© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4795
    Prev
    Next
    INDEX
    Explanations

    phrases related to freedom and justice

    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
    285
    +0.12
    0.6%
    736
    +0.10
    0.5%
    626
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.12
    0.05
    449
    +0.10
    0.04
    560
    +0.10
    0.03
    Negative Logits
    Hart
    -0.70
    Factor
    -0.66
    Âł
    -0.65
    ";
    -0.65
     approx
    -0.64
     Retrieved
    -0.63
    ËĪ
    -0.63
    HOU
    -0.62
    CBC
    -0.62
    DOC
    -0.61
    POSITIVE LOGITS
     meanwhile
    0.99
    nce
    0.99
    neath
    0.97
     moreover
    0.85
     therefore
    0.82
    anwhile
    0.81
    theless
    0.80
    ichever
    0.79
    beit
    0.77
     however
    0.76
    Activations Density 0.522%

    No Known Activations