© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5711
    Prev
    Next
    INDEX
    Explanations

    instances of auditory and visual perceptions

    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
    29
    +0.11
    0.5%
    765
    +0.10
    0.5%
    766
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    486
    +0.11
    0.04
    403
    +0.10
    0.04
    218
    +0.10
    0.04
    Negative Logits
    ove
    -0.78
    lator
    -0.76
    ItemTracker
    -0.75
    vic
    -0.73
    enthal
    -0.72
    ãĤ´ãĥ³
    -0.71
    pdf
    -0.70
    tested
    -0.69
    youtube
    -0.69
    utical
    -0.69
    POSITIVE LOGITS
     faint
    0.89
     nothing
    0.86
     flashing
    0.85
     footsteps
    0.84
     someone
    0.82
     headlights
    0.81
     flickering
    0.81
     helicopters
    0.79
     flashes
    0.78
     silhou
    0.78
    Activations Density 0.266%

    No Known Activations