© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4397
    Prev
    Next
    INDEX
    Explanations

    mentions of division or separation, particularly in contexts relating to choices or options

    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
    373
    +0.12
    0.6%
    84
    +0.09
    0.5%
    273
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.12
    0.02
    639
    +0.09
    0.02
    20
    +0.09
    0.02
    Negative Logits
     Scrib
    -0.81
     Hip
    -0.63
     Instruments
    -0.62
     Shooter
    -0.61
     Targ
    -0.59
     Simulation
    -0.56
     achie
    -0.56
     Herald
    -0.56
     guid
    -0.55
     Defenders
    -0.55
    POSITIVE LOGITS
    or
    0.99
    possibly
    0.91
    probably
    0.90
    usually
    0.88
    especially
    0.87
    entimes
    0.82
    perhaps
    0.81
    orah
    0.80
    sometimes
    0.80
    mostly
    0.80
    Activations Density 0.021%

    No Known Activations