© 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. 29952
    Prev
    Next
    INDEX
    Explanations

    mentions of gaming-related terms or entities

    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
    347
    +0.12
    0.6%
    314
    +0.12
    0.5%
    621
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.02
    526
    +0.12
    0.00
    314
    +0.10
    0.00
    Negative Logits
     consec
    -0.71
     condem
    -0.69
     FISA
    -0.65
     Cheong
    -0.63
     helic
    -0.62
     Hawth
    -0.59
     plur
    -0.58
     Parish
    -0.58
     Grounds
    -0.56
    ENCE
    -0.55
    POSITIVE LOGITS
    blers
    1.44
    etime
    1.31
    bit
    1.26
    estate
    1.18
    bitious
    1.16
    emaker
    1.11
    boa
    1.11
    estone
    1.10
    ma
    1.09
    eworks
    1.08
    Activations Density 0.069%

    No Known Activations