© 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. 31588
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of continuity

    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
    459
    +0.11
    0.5%
    207
    +0.10
    0.5%
    488
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.11
    0.01
    404
    +0.10
    0.02
    288
    +0.09
    0.03
    Negative Logits
    eah
    -0.70
    assic
    -0.65
    illet
    -0.64
    Sov
    -0.64
    IFA
    -0.64
    natureconservancy
    -0.63
    HCR
    -0.62
    gdala
    -0.61
    */(
    -0.61
    rely
    -0.61
    POSITIVE LOGITS
    uity
    1.03
    uum
    0.99
    uously
    0.95
    ial
    0.90
    uous
    0.88
    ials
    0.86
    grain
    0.86
    ental
    0.83
    uations
    0.79
     Integration
    0.78
    Activations Density 0.137%

    No Known Activations