© 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. 26931
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intention

    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
    373
    +0.12
    0.6%
    369
    +0.11
    0.5%
    512
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.12
    0.05
    730
    +0.11
    0.06
    566
    +0.10
    0.05
    Negative Logits
     intervening
    -0.65
    heimer
    -0.65
     takeover
    -0.64
    uf
    -0.61
    ysis
    -0.61
     moot
    -0.61
    ullah
    -0.60
     foregoing
    -0.59
    meet
    -0.58
     undergoing
    -0.58
    POSITIVE LOGITS
     someone
    0.79
     something
    0.79
     somebody
    0.75
     people
    0.72
    initely
    0.70
    rals
    0.69
    asty
    0.69
     folks
    0.68
     everyone
    0.67
    someone
    0.66
    Activations Density 0.343%

    No Known Activations