© 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. 29582
    Prev
    Next
    INDEX
    Explanations

    elements that contribute to depth and richness in descriptions or narratives

    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
    282
    +0.15
    0.7%
    426
    +0.14
    0.7%
    414
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.15
    0.11
    426
    +0.14
    0.07
    408
    +0.11
    0.12
    Negative Logits
    sites
    -0.82
    ebook
    -0.77
    agents
    -0.72
    ware
    -0.66
    CD
    -0.66
    zilla
    -0.65
    pleted
    -0.64
    imens
    -0.64
    apers
    -0.64
    MQ
    -0.63
    POSITIVE LOGITS
     elegance
    1.25
     individuality
    1.23
     uniqueness
    1.22
     authenticity
    1.22
     charm
    1.20
     warmth
    1.20
     realism
    1.20
     depth
    1.18
     nuance
    1.16
     flair
    1.13
    Activations Density 1.550%

    No Known Activations