© 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. 27307
    Prev
    Next
    INDEX
    Explanations

    references to events and their timing

    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
    146
    +0.12
    0.5%
    666
    +0.11
    0.5%
    745
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.07
    616
    +0.11
    0.05
    608
    +0.10
    0.07
    Negative Logits
    ãĤ¤ãĥĪ
    -0.85
    ãĥ³ãĤ¸
    -0.82
    theless
    -0.77
    leck
    -0.71
    alia
    -0.70
    bilt
    -0.69
    regon
    -0.66
     Courage
    -0.63
    iences
    -0.63
    allery
    -0.62
    POSITIVE LOGITS
     date
    1.69
     expiration
    1.36
     commencement
    1.32
     dates
    1.22
     anniversary
    1.21
     completion
    1.19
     filing
    1.18
     enactment
    1.17
     deadline
    1.15
    date
    1.08
    Activations Density 0.496%

    No Known Activations