© 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. 5400
    Prev
    Next
    INDEX
    Explanations

    titles of artistic works or references to creative entities

    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
    453
    +0.10
    0.4%
    234
    +0.09
    0.4%
    684
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.03
    374
    +0.09
    0.01
    373
    +0.09
    -0.02
    Negative Logits
     Feder
    -0.69
    ships
    -0.68
     jurisdiction
    -0.67
     Teams
    -0.62
    ccording
    -0.62
     Europa
    -0.62
     IST
    -0.61
    BIL
    -0.60
     metab
    -0.59
     Tau
    -0.59
    POSITIVE LOGITS
    hew
    0.76
     Mahjong
    0.70
    aper
    0.69
    Buzz
    0.67
    iolet
    0.66
    âĢ¢âĢ¢
    0.65
    heny
    0.65
    ï
    0.65
    uncle
    0.64
    yip
    0.63
    Activations Density 0.173%

    No Known Activations