© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29426
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition results and tournament structures

    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
    +0.12
    0.6%
    133
    +0.10
    0.4%
    149
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.12
    0.06
    281
    +0.10
    0.04
    460
    +0.10
    0.04
    Negative Logits
    uti
    -0.77
    dylib
    -0.76
     offensively
    -0.74
    gur
    -0.71
    âĹ¼
    -0.70
    agency
    -0.65
     barking
    -0.65
     stunts
    -0.63
    atility
    -0.62
    usage
    -0.61
    POSITIVE LOGITS
     semifinals
    1.23
    finals
    1.14
     losers
    1.11
     finals
    1.09
     Finals
    1.08
     seeded
    1.07
     loser
    1.07
     qualifier
    1.05
     bracket
    1.02
     Sem
    1.01
    Activations Density 1.121%

    No Known Activations