© 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. 7266
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements

    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
    140
    +0.11
    0.5%
    210
    +0.11
    0.5%
    318
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.11
    0.03
    373
    +0.11
    -0.03
    627
    +0.11
    0.01
    Negative Logits
    Sim
    -0.81
    ioxide
    -0.79
    obin
    -0.78
     OC
    -0.78
     Schne
    -0.77
     Circ
    -0.76
     Sim
    -0.76
     circ
    -0.76
     Astro
    -0.74
     Cran
    -0.73
    POSITIVE LOGITS
    50
    1.31
     50
    1.20
     Fifty
    1.12
     51
    1.06
    ifty
    1.04
    49
    1.01
    51
    1.01
     49
    0.97
     fifty
    0.93
     Vill
    0.91
    Activations Density 0.642%

    No Known Activations