© 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. 7776
    Prev
    Next
    INDEX
    Explanations

    instances of the word "put."

    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
    314
    +0.13
    0.6%
    373
    +0.11
    0.5%
    13
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.13
    0.05
    761
    +0.11
    0.04
    411
    +0.10
    0.04
    Negative Logits
     reuse
    -0.58
     Vincent
    -0.57
     Patterns
    -0.57
     forgiveness
    -0.57
     Examination
    -0.56
     remnant
    -0.55
    issance
    -0.55
    vine
    -0.54
     Binary
    -0.54
     Heist
    -0.54
    POSITIVE LOGITS
    rid
    0.95
     forth
    0.94
    atively
    0.94
    ative
    0.86
    uph
    0.84
    tin
    0.83
    onom
    0.83
    downs
    0.81
    ongh
    0.79
     together
    0.79
    Activations Density 0.078%

    No Known Activations