© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4462
    Prev
    Next
    INDEX
    Explanations

    phrases or references indicating a source or origin

    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
    314
    +0.13
    0.6%
    62
    +0.11
    0.5%
    412
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.13
    0.06
    669
    +0.11
    0.04
    157
    +0.10
    0.04
    Negative Logits
    reality
    -0.74
    ĺħ
    -0.69
    rations
    -0.68
    Ħ¢
    -0.68
    xual
    -0.68
    EStreamFrame
    -0.67
    resy
    -0.65
    ordinary
    -0.64
    role
    -0.63
     society
    -0.62
    POSITIVE LOGITS
     September
    1.10
     June
    1.10
     July
    1.09
     January
    1.08
     February
    1.08
     November
    1.03
     April
    1.03
     August
    1.02
     October
    1.00
     March
    0.99
    Activations Density 0.257%

    No Known Activations