© 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. 5354
    Prev
    Next
    INDEX
    Explanations

    significant phrases and titles from films and songs

    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
    314
    +0.14
    0.6%
    84
    +0.12
    0.5%
    430
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.14
    0.05
    572
    +0.12
    0.05
    183
    +0.11
    0.03
    Negative Logits
     propag
    -0.72
     rental
    -0.71
     dependency
    -0.71
     precip
    -0.70
     conspic
    -0.69
     graph
    -0.69
     req
    -0.68
     deficiency
    -0.68
     exacerb
    -0.68
     mitigating
    -0.68
    POSITIVE LOGITS
     Shall
    1.07
     Things
    1.02
     Eternity
    1.01
     Wonderful
    0.97
     Lies
    0.95
     Tomorrow
    0.95
     Love
    0.94
     Horses
    0.93
     Enough
    0.93
     Yourself
    0.93
    Activations Density 0.488%

    No Known Activations