© 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. 7503
    Prev
    Next
    INDEX
    Explanations

    references to socio-political events and conditions

    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
    53
    +0.09
    0.4%
    557
    +0.09
    0.4%
    548
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.28
    575
    +0.09
    0.25
    225
    +0.09
    0.18
    Negative Logits
     haw
    -0.67
    rollers
    -0.57
     sparing
    -0.54
     mature
    -0.54
    irs
    -0.54
     bluff
    -0.54
     waivers
    -0.52
    Balt
    -0.51
    vere
    -0.51
     relent
    -0.51
    POSITIVE LOGITS
     violates
    0.87
     illustrates
    0.86
     constitutes
    0.83
     underscores
    0.82
    ?,
    0.82
     reinforces
    0.79
    .?
    0.79
     ignores
    0.79
     suggests
    0.78
    ?",
    0.78
    Activations Density 7.924%

    No Known Activations