© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9024
    Prev
    Next
    INDEX
    Explanations

    instances of the character "L" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    421
    +0.12
    0.6%
    314
    +0.12
    0.6%
    141
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.12
    0.13
    6
    +0.12
    0.12
    48
    +0.11
    0.10
    Negative Logits
    ktop
    -0.74
     sclerosis
    -0.69
     reap
    -0.69
    rieve
    -0.68
    seless
    -0.66
    kson
    -0.66
     endings
    -0.64
    chnology
    -0.60
     indictment
    -0.59
     plur
    -0.59
    POSITIVE LOGITS
    ãĤ±
    0.99
    ãģĨ
    0.96
    é¾į
    0.84
    ¼
    0.83
    äºĶ
    0.81
    èĢ
    0.76
    owl
    0.76
    Ĭ
    0.76
    ļ
    0.75
    committee
    0.74
    Activations Density 0.333%

    No Known Activations