© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 31497
    Prev
    Next
    INDEX
    Explanations

    references to inclusivity and the concept of "all" or the collective participation of groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    274
    +0.11
    0.5%
    563
    +0.10
    0.5%
    418
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    637
    +0.11
    0.05
    237
    +0.10
    0.04
    113
    +0.10
    0.03
    Negative Logits
     Schwar
    -0.72
     Absent
    -0.63
    LESS
    -0.61
    OLOGY
    -0.60
    ça
    -0.60
    uberty
    -0.59
    ukemia
    -0.58
     ----------------------------------------------------------------
    -0.57
    zar
    -0.57
    bestos
    -0.57
    POSITIVE LOGITS
     shapes
    1.19
     angles
    1.17
     directions
    1.15
     sides
    1.14
     stripes
    1.14
     kinds
    1.07
     varieties
    1.04
     sizes
    1.04
     fronts
    1.02
     sorts
    1.01
    Activations Density 0.291%

    No Known Activations