© 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. 7263
    Prev
    Next
    INDEX
    Explanations

    numerical values and identifiers related to hashes or encoded data

    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
    +0.13
    0.6%
    756
    +0.10
    0.5%
    745
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.05
    153
    +0.10
    0.05
    488
    +0.10
    0.04
    Negative Logits
     divisions
    -0.79
     Packs
    -0.72
     leagues
    -0.67
     towels
    -0.66
     factions
    -0.65
     lenders
    -0.65
     economies
    -0.65
     destinations
    -0.64
     TVs
    -0.64
     centers
    -0.64
    POSITIVE LOGITS
    aye
    0.94
    ecd
    0.89
    aea
    0.81
    aba
    0.81
    abe
    0.79
    afa
    0.78
    bf
    0.77
    eor
    0.77
    efe
    0.76
    df
    0.76
    Activations Density 0.209%

    No Known Activations