© 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. 5355
    Prev
    Next
    INDEX
    Explanations

    references to "Wall Street" and related financial contexts

    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
    527
    +0.11
    0.5%
    575
    +0.09
    0.4%
    442
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.11
    0.02
    482
    +0.09
    0.01
    288
    +0.09
    0.02
    Negative Logits
    imum
    -0.71
    essa
    -0.70
    864
    -0.70
    OPLE
    -0.70
    ãĥĺ
    -0.69
    toc
    -0.69
    vim
    -0.68
    wik
    -0.67
    VALUE
    -0.67
    ELY
    -0.67
    POSITIVE LOGITS
     Journal
    1.26
     firms
    0.86
     Banking
    0.75
     Journals
    0.75
     Quarterly
    0.72
     bankers
    0.72
     analysts
    0.72
     executives
    0.72
     Conference
    0.70
    rollers
    0.70
    Activations Density 0.098%

    No Known Activations