© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 7019
    Prev
    Next
    INDEX
    Explanations

    occurrences of movie and comic book franchise titles and characters

    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
    172
    +0.12
    0.5%
    119
    +0.11
    0.5%
    748
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.12
    0.02
    326
    +0.11
    0.05
    364
    +0.10
    0.04
    Negative Logits
    esse
    -0.64
     Osw
    -0.62
    swick
    -0.62
    arters
    -0.61
    heit
    -0.61
    ADVERTISEMENT
    -0.60
    ufact
    -0.60
    iage
    -0.60
     passage
    -0.58
    ItemTracker
    -0.58
    POSITIVE LOGITS
    reme
    0.95
    Large
    0.73
    ©¶æ
    0.69
     Related
    0.67
     Movies
    0.66
    toc
    0.66
    thur
    0.66
    bia
    0.65
    ĪĴ
    0.63
    acion
    0.63
    Activations Density 0.680%

    No Known Activations