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. 5070
    Prev
    Next
    INDEX
    Explanations

    the term "Quick" and its variations, likely in relation to a cycling team or brand

    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
    457
    +0.08
    0.4%
    360
    +0.08
    0.4%
    636
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.08
    0.04
    288
    +0.08
    0.04
    232
    +0.08
    0.04
    Negative Logits
    antic
    -0.69
    entric
    -0.69
    RPG
    -0.68
    »Ĵ
    -0.67
    hovah
    -0.66
    Īè
    -0.62
     DOI
    -0.61
    aded
    -0.61
    itals
    -0.60
     appendix
    -0.60
    POSITIVE LOGITS
    ying
    0.91
    field
    0.90
    lied
    0.84
    minster
    0.82
    faces
    0.80
    housing
    0.80
    ware
    0.79
    mere
    0.76
    leaf
    0.76
    ly
    0.76
    Activations Density 0.191%

    No Known Activations