© 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 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. 29181
    Prev
    Next
    INDEX
    Explanations

    references to the concept of duality or pairs

    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
    129
    +0.10
    0.5%
    49
    +0.09
    0.4%
    403
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.10
    0.05
    327
    +0.09
    0.03
    221
    +0.09
    0.03
    Negative Logits
    xus
    -1.06
    renheit
    -0.81
    terday
    -0.80
    zzle
    -0.78
    istle
    -0.77
    obyl
    -0.74
    utenant
    -0.74
    ighth
    -0.74
    utor
    -0.73
     teasp
    -0.73
    POSITIVE LOGITS
     phenomena
    1.23
     extremes
    1.14
     entities
    1.10
     situations
    1.10
     groups
    1.08
     concepts
    1.07
     parties
    1.05
     endeavors
    1.04
     types
    1.03
     organizations
    1.01
    Activations Density 0.192%

    No Known Activations