Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 6-RES_POST_32K-OAI
    6. 4203
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly highlighting significant figures or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    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
    339
    +0.11
    0.5%
    19
    +0.10
    0.5%
    216
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    719
    +0.11
    0.04
    6
    +0.10
    0.04
    415
    +0.10
    0.03
    Negative Logits
    xual
    -0.97
     Flavoring
    -0.75
    ansas
    -0.68
    staking
    -0.67
    xon
    -0.64
    itude
    -0.64
    iosis
    -0.63
    eer
    -0.63
    onis
    -0.62
    by
    -0.62
    POSITIVE LOGITS
    dfx
    1.27
    ovember
    0.81
    wu
    0.76
    OTE
    0.74
    asted
    0.73
    plays
    0.73
     Minutes
    0.73
    arget
    0.73
    468
    0.72
     cents
    0.71
    Activations Density 0.082%

    No Known Activations