© 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. 4681
    Prev
    Next
    INDEX
    Explanations

    references to specific characters and their roles within narratives

    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
    408
    +0.12
    0.6%
    422
    +0.10
    0.4%
    581
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.06
    757
    +0.10
    0.04
    718
    +0.09
    0.05
    Negative Logits
    ahime
    -0.84
     DRAG
    -0.65
    uay
    -0.63
     Cosponsors
    -0.63
     [|
    -0.61
    §
    -0.60
     Dungeon
    -0.59
    tnc
    -0.59
    ensions
    -0.57
    Ĥİ
    -0.56
    POSITIVE LOGITS
     truly
    1.01
     ever
    0.97
     remotely
    0.96
     anymore
    0.95
     reliably
    0.93
     definitively
    0.91
     sane
    0.91
     EVER
    0.89
     usable
    0.85
     semblance
    0.85
    Activations Density 0.708%

    No Known Activations