© 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. 8-RES_POST_32K-OAI
    11. 7925
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    373
    +0.17
    0.8%
    218
    +0.12
    0.6%
    572
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.17
    0.06
    218
    +0.12
    0.04
    287
    +0.12
    0.04
    Negative Logits
    venture
    -0.67
     Cosponsors
    -0.65
    clave
    -0.64
    iggins
    -0.60
    akens
    -0.57
    ixel
    -0.57
    ensical
    -0.55
    atile
    -0.55
    emon
    -0.53
    ilitary
    -0.53
    POSITIVE LOGITS
     anybody
    0.96
     ya
    0.96
     you
    0.86
    tha
    0.86
     anyone
    0.83
     somebody
    0.81
     YOU
    0.73
     there
    0.73
     someone
    0.69
     yo
    0.65
    Activations Density 0.225%

    No Known Activations