© 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. 4869
    Prev
    Next
    INDEX
    Explanations

    references to live events or broadcasts

    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
    405
    +0.10
    0.5%
    241
    +0.10
    0.4%
    509
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.10
    0.02
    257
    +0.10
    0.02
    359
    +0.09
    0.02
    Negative Logits
    IBLE
    -0.90
     noise
    -0.76
     fumes
    -0.65
     horse
    -0.65
     sockets
    -0.65
    ifiers
    -0.64
     overt
    -0.64
     air
    -0.64
     dummy
    -0.63
     sourcing
    -0.63
    POSITIVE LOGITS
    lihood
    1.13
    acre
    0.91
    Story
    0.90
    Way
    0.87
     Matters
    0.84
    NOW
    0.81
    isure
    0.79
    vant
    0.79
    ira
    0.77
    olitan
    0.77
    Activations Density 0.206%

    No Known Activations