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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5188
    Prev
    Next
    INDEX
    Explanations

    URLs and links references

    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
    170
    +0.11
    0.5%
    373
    +0.10
    0.5%
    442
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.04
    373
    +0.10
    -0.01
    442
    +0.10
    0.03
    Negative Logits
     accomp
    -0.77
    rily
    -0.64
     Dates
    -0.64
     whom
    -0.63
     includ
    -0.62
     shortage
    -0.62
     conclud
    -0.62
     grate
    -0.61
     attribution
    -0.60
     dates
    -0.59
    POSITIVE LOGITS
    76561
    0.95
    DragonMagazine
    0.84
    monary
    0.74
    ctrl
    0.73
     Benson
    0.69
    UE
    0.69
    adder
    0.69
    aram
    0.68
    BF
    0.68
    FU
    0.67
    Activations Density 0.130%

    No Known Activations