© 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. 10-RES_POST_32K-OAI
    11. 32082
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'm' in varying contexts

    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
    314
    +0.11
    0.5%
    368
    +0.10
    0.5%
    427
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.10
    314
    +0.10
    0.00
    103
    +0.10
    0.04
    Negative Logits
    tons
    -0.66
     rh
    -0.64
     shortfall
    -0.63
     grounded
    -0.63
    ãĥł
    -0.62
     slips
    -0.62
     ashes
    -0.61
     hostages
    -0.61
     scrut
    -0.60
     scant
    -0.60
    POSITIVE LOGITS
    ixtape
    0.87
    afia
    0.83
    oto
    0.82
    MO
    0.81
    SPA
    0.78
    ocker
    0.72
    otos
    0.72
    aven
    0.72
    iku
    0.72
    oka
    0.72
    Activations Density 0.633%

    No Known Activations