© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29794
    Prev
    Next
    INDEX
    Explanations

    structural elements and complexity in data or arguments

    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
    425
    +0.15
    0.7%
    9
    +0.13
    0.6%
    737
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.09
    409
    +0.13
    0.06
    48
    +0.13
    0.05
    Negative Logits
    Gall
    -1.02
     Ell
    -0.99
     Gall
    -0.99
     Ken
    -0.91
     Jenkins
    -0.89
     Jess
    -0.86
    Ken
    -0.83
     Opp
    -0.83
     Clarks
    -0.83
     Box
    -0.82
    POSITIVE LOGITS
    vere
    1.01
    Shar
    0.95
    ims
    0.89
    icum
    0.87
     shar
    0.86
    Var
    0.86
    cre
    0.82
    vi
    0.79
    ubis
    0.79
    vin
    0.79
    Activations Density 6.566%

    No Known Activations