© 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. 8-RES_POST_32K-OAI
    11. 4626
    Prev
    Next
    INDEX
    Explanations

    mentions of "fiction" and its various genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    556
    +0.10
    0.5%
    32
    +0.10
    0.5%
    274
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.04
    575
    +0.10
    0.03
    401
    +0.10
    0.03
    Negative Logits
    nas
    -0.79
    baugh
    -0.79
    tics
    -0.78
    lain
    -0.76
    umm
    -0.76
    holder
    -0.75
    holders
    -0.75
    mma
    -0.74
    arov
    -0.71
    motion
    -0.71
    POSITIVE LOGITS
     fiction
    1.03
     novelist
    0.89
     Fiction
    0.84
     novel
    0.80
     thriller
    0.78
     novels
    0.78
    fiction
    0.70
     theorist
    0.70
    ishly
    0.70
     films
    0.70
    Activations Density 0.196%

    No Known Activations