© 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. 10-RES_POST_32K-OAI
    6. 29677
    Prev
    Next
    INDEX
    Explanations

    references to time durations and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    377
    +0.10
    0.4%
    706
    +0.09
    0.4%
    727
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.10
    0.04
    727
    +0.09
    0.03
    383
    +0.09
    0.03
    Negative Logits
    idth
    -0.79
     Adds
    -0.77
    rium
    -0.69
     Coverage
    -0.64
    });
    -0.63
    opia
    -0.60
     Starts
    -0.60
    orthy
    -0.59
     acknowledgment
    -0.59
    intendent
    -0.58
    POSITIVE LOGITS
     immersed
    1.02
     embroiled
    0.89
     glued
    0.87
     trapped
    0.87
     agon
    0.85
     hol
    0.83
     surrounded
    0.82
     staring
    0.81
     locked
    0.81
     tangled
    0.81
    Activations Density 0.177%

    No Known Activations