© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5813
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and categorization

    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
    679
    +0.12
    0.5%
    288
    +0.12
    0.5%
    161
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    161
    +0.12
    0.01
    507
    +0.10
    0.02
    Negative Logits
    perty
    -0.84
    elin
    -0.76
    vous
    -0.75
     Tah
    -0.70
    hire
    -0.66
    haw
    -0.66
    issance
    -0.65
     ful
    -0.64
    fare
    -0.63
    Ħ¢
    -0.61
    POSITIVE LOGITS
    ifiers
    0.90
    ifier
    0.90
    ifications
    0.85
     CPC
    0.85
    ifiable
    0.84
    ically
    0.81
    ename
    0.79
    itatively
    0.77
    rill
    0.76
    untarily
    0.76
    Activations Density 0.067%

    No Known Activations