© 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. 31521
    Prev
    Next
    INDEX
    Explanations

    instances of the word "all," indicating a focus on totality or completeness

    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
    693
    +0.11
    0.5%
    97
    +0.10
    0.5%
    110
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.11
    0.06
    637
    +0.10
    0.06
    237
    +0.10
    0.05
    Negative Logits
    nor
    -0.65
     counterpart
    -0.64
    Prop
    -0.61
     predecessor
    -0.60
    vg
    -0.59
     however
    -0.59
    etheless
    -0.58
    VP
    -0.57
     interven
    -0.57
     rendering
    -0.57
    POSITIVE LOGITS
     kinds
    1.06
     sorts
    1.01
     these
    0.85
    ahu
    0.82
     those
    0.77
    igators
    0.76
    these
    0.76
     fuckin
    0.74
     sudden
    0.73
     kind
    0.71
    Activations Density 0.237%

    No Known Activations