© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5172
    Prev
    Next
    INDEX
    Explanations

    question marks and other symbols indicating queries or requests for information

    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
    107
    +0.10
    0.5%
    742
    +0.10
    0.4%
    667
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.10
    0.02
    558
    +0.10
    0.01
    314
    +0.10
    0.00
    Negative Logits
     Grimm
    -0.77
    theless
    -0.76
     Gron
    -0.75
     Blackwell
    -0.74
     Ãľ
    -0.71
     surges
    -0.68
     Dise
    -0.68
     Eag
    -0.67
     Gilmore
    -0.67
     Reck
    -0.65
    POSITIVE LOGITS
    section
    0.95
    topic
    0.93
    pid
    0.90
    CVE
    0.89
    pi
    0.89
    toc
    0.88
    mt
    0.88
    acl
    0.87
    menu
    0.85
    project
    0.84
    Activations Density 0.126%

    No Known Activations