© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4357
    Prev
    Next
    INDEX
    Explanations

    paths and directories in a filesystem, particularly home directories and configuration files

    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
    373
    +0.13
    0.6%
    314
    +0.11
    0.5%
    257
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.13
    0.03
    326
    +0.11
    0.03
    284
    +0.10
    0.02
    Negative Logits
    boro
    -0.66
    acca
    -0.65
     unheard
    -0.64
     understatement
    -0.64
     detract
    -0.62
    erence
    -0.61
     surrogate
    -0.61
     âī¤
    -0.61
     constituent
    -0.60
     approximation
    -0.60
    POSITIVE LOGITS
    bash
    1.14
    desktop
    1.03
    config
    1.00
    local
    0.99
    vim
    0.96
    minecraft
    0.92
    profile
    0.91
    cfg
    0.90
    env
    0.84
    ssh
    0.83
    Activations Density 0.094%

    No Known Activations