© 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. 32056
    Prev
    Next
    INDEX
    Explanations

    instances of "ec" in various contexts, likely indicating a focus on ecological or economic themes

    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
    288
    +0.12
    0.5%
    314
    +0.10
    0.5%
    598
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.01
    701
    +0.10
    0.01
    746
    +0.10
    0.01
    Negative Logits
     dear
    -0.65
     Lucifer
    -0.64
     Rouse
    -0.63
     Colt
    -0.62
     Desire
    -0.62
     rall
    -0.61
     grapp
    -0.60
     fire
    -0.58
     Werewolf
    -0.57
     Rapp
    -0.57
    POSITIVE LOGITS
    stasy
    1.34
    uador
    1.25
    lectic
    1.21
    essors
    1.12
    essor
    1.02
    osta
    1.02
    utive
    1.01
    urity
    1.00
    heon
    1.00
    ounters
    0.98
    Activations Density 0.079%

    No Known Activations