© 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. 7930
    Prev
    Next
    INDEX
    Explanations

    expressions related to restraint or avoidance of actions

    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
    204
    +0.12
    0.6%
    153
    +0.09
    0.4%
    744
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.06
    204
    +0.09
    0.05
    611
    +0.09
    0.05
    Negative Logits
    enery
    -0.73
    ovsky
    -0.69
     Boom
    -0.67
    rupted
    -0.66
     misunderstood
    -0.63
    owski
    -0.61
    etsk
    -0.61
    uttered
    -0.60
    iverse
    -0.59
    ernels
    -0.59
    POSITIVE LOGITS
     invitations
    0.90
     altogether
    0.90
     disclosing
    0.89
     endorsing
    0.89
     mentioning
    0.88
     commenting
    0.88
     criticizing
    0.88
     admitting
    0.87
     outright
    0.85
     recommending
    0.84
    Activations Density 0.538%

    No Known Activations