© 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. 5310
    Prev
    Next
    INDEX
    Explanations

    references to different types of arrays and matrix structures in programming

    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
    616
    +0.13
    0.6%
    289
    +0.10
    0.5%
    513
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.13
    0.02
    678
    +0.10
    0.02
    616
    +0.10
    0.02
    Negative Logits
    dom
    -0.77
    doms
    -0.74
    é¾įå¥ij士
    -0.69
     Gork
    -0.64
    mins
    -0.63
    cia
    -0.60
    hua
    -0.60
    lasses
    -0.59
    ews
    -0.58
     Dame
    -0.58
    POSITIVE LOGITS
     subscript
    0.87
    uably
    0.80
    Buffer
    0.74
    adium
    0.70
    mble
    0.68
    itect
    0.66
    icter
    0.66
     sizes
    0.65
    antine
    0.65
    ansas
    0.64
    Activations Density 0.067%

    No Known Activations