© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26560
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities

    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
    617
    +0.11
    0.5%
    124
    +0.11
    0.5%
    300
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.11
    0.08
    223
    +0.11
    0.08
    344
    +0.11
    0.08
    Negative Logits
    igger
    -0.68
    >:
    -0.65
    "]=>
    -0.65
    ovan
    -0.58
    Join
    -0.56
     Hancock
    -0.56
    sonian
    -0.55
    gewater
    -0.55
    >[
    -0.54
    MSN
    -0.53
    POSITIVE LOGITS
     thereafter
    1.01
     respectively
    0.91
     apiece
    0.84
     elsewhere
    0.83
     others
    0.80
     afterward
    0.72
     afterwards
    0.71
     were
    0.66
     if
    0.66
     are
    0.66
    Activations Density 1.251%

    No Known Activations