© 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. 4928
    Prev
    Next
    INDEX
    Explanations

    geographical references and locations in text

    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
    478
    +0.10
    0.5%
    205
    +0.10
    0.5%
    700
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.10
    546
    +0.10
    0.10
    765
    +0.10
    0.10
    Negative Logits
    ename
    -0.67
    href
    -0.65
    orem
    -0.65
    ograp
    -0.65
    rupted
    -0.64
    mberg
    -0.63
    pheus
    -0.63
    zeb
    -0.62
    ="#
    -0.61
    uria
    -0.61
    POSITIVE LOGITS
     respectively
    2.52
    depending
    1.55
     alike
    1.48
     depending
    1.11
     whichever
    0.97
    etc
    0.93
     among
    0.88
    among
    0.87
     respective
    0.86
     etc
    0.82
    Activations Density 1.672%

    No Known Activations