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

    Neuronpedia

    Jacobian LensNEW
    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. 6950
    Prev
    Next
    INDEX
    Explanations

    references to ABC News and its associated elements

    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
    417
    +0.12
    0.6%
    286
    +0.11
    0.5%
    208
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.12
    0.02
    159
    +0.11
    0.02
    417
    +0.10
    0.02
    Negative Logits
    crop
    -0.66
     sclerosis
    -0.63
    cloth
    -0.63
    wagen
    -0.63
    vik
    -0.61
    amoto
    -0.61
    creen
    -0.59
    hander
    -0.58
     Jays
    -0.58
    pora
    -0.58
    POSITIVE LOGITS
    DEF
    1.32
    NEWS
    1.02
    sonian
    0.82
    LI
    0.78
    nect
    0.77
    ICLE
    0.77
    elaide
    0.76
    RL
    0.76
    IS
    0.74
    icut
    0.74
    Activations Density 0.055%

    No Known Activations