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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4941
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps

    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%
    373
    +0.12
    0.5%
    672
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    567
    +0.13
    0.02
    749
    +0.12
    0.02
    598
    +0.10
    0.01
    Negative Logits
    yss
    -0.85
    achus
    -0.75
    uliffe
    -0.73
    inia
    -0.69
    ructose
    -0.69
    fman
    -0.67
    achev
    -0.66
    renheit
    -0.66
    ieu
    -0.66
    igne
    -0.64
    POSITIVE LOGITS
    renched
    0.63
     Wed
    0.62
     enactment
    0.58
     indisc
    0.57
     Snapchat
    0.57
     Tup
    0.57
    Sent
    0.56
    pal
    0.56
     Instagram
    0.56
    ASED
    0.56
    Activations Density 0.153%

    No Known Activations