© 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. 8184
    Prev
    Next
    INDEX
    Explanations

    technical specifications and numerical data related to devices or products

    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
    674
    +0.10
    0.5%
    557
    +0.10
    0.4%
    696
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.10
    0.07
    748
    +0.10
    0.04
    220
    +0.09
    0.05
    Negative Logits
    matter
    -0.76
    eve
    -0.74
    amon
    -0.73
     experien
    -0.69
    olitics
    -0.69
    icism
    -0.66
    doing
    -0.66
    idays
    -0.65
    ivism
    -0.65
     miscarriage
    -0.64
    POSITIVE LOGITS
     additional
    1.01
     assorted
    0.89
     adjustable
    0.89
     spare
    0.89
     removable
    0.81
     complimentary
    0.78
     optional
    0.76
     supplemental
    0.75
     auxiliary
    0.75
     customizable
    0.74
    Activations Density 0.415%

    No Known Activations