© 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 EvalsExportsinterp-engineNEWAPI 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. 7384
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "AP" and its variations in context

    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
    238
    +0.12
    0.5%
    101
    +0.08
    0.4%
    683
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.03
    373
    +0.08
    -0.01
    314
    +0.08
    0.00
    Negative Logits
     defic
    -0.64
    omes
    -0.64
     obser
    -0.63
     suspic
    -0.62
     spitting
    -0.59
     hus
    -0.59
     mascul
    -0.58
     Maxwell
    -0.58
     Joined
    -0.57
     Haas
    -0.56
    POSITIVE LOGITS
    eways
    0.98
    olitan
    0.92
    hess
    0.90
    eway
    0.90
    TOP
    0.88
    TOR
    0.88
    tions
    0.87
    lar
    0.82
    roxy
    0.81
    erton
    0.81
    Activations Density 0.144%

    No Known Activations