© 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 EvalsExportsAPI 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. 28248
    Prev
    Next
    INDEX
    Explanations

    terms related to the classification and behavior of various creatures and items in a gaming or fictional context

    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
    343
    +0.11
    0.5%
    549
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    232
    +0.11
    0.03
    588
    +0.11
    0.03
    Negative Logits
    çīĪ
    -0.77
    ħĭ
    -0.69
     stricken
    -0.61
     captcha
    -0.60
    Reviewer
    -0.60
     shutter
    -0.60
    CAST
    -0.60
    oak
    -0.59
    Fax
    -0.58
    pter
    -0.58
    POSITIVE LOGITS
    ions
    1.20
    ion
    1.12
    ione
    1.04
    rael
    1.01
    ION
    0.95
    io
    0.93
    arian
    0.90
    ities
    0.90
    ario
    0.89
    ional
    0.89
    Activations Density 0.152%

    No Known Activations