© 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. 6423
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating potential actions or outcomes

    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
    361
    +0.11
    0.5%
    241
    +0.10
    0.4%
    319
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.11
    0.13
    139
    +0.10
    0.12
    718
    +0.10
    0.10
    Negative Logits
     ACTIONS
    -0.69
     Pon
    -0.67
     Trial
    -0.67
     Activities
    -0.66
     Jur
    -0.65
    hered
    -0.64
     Acad
    -0.64
     ALP
    -0.63
     Organizations
    -0.63
    unal
    -0.63
    POSITIVE LOGITS
     suffice
    1.24
    afort
    0.97
     elicit
    0.85
     alleviate
    0.84
     necess
    0.79
     attest
    0.76
    idates
    0.75
    sis
    0.74
     insure
    0.74
    hap
    0.74
    Activations Density 0.673%

    No Known Activations