© 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. 4196
    Prev
    Next
    INDEX
    Explanations

    terms associated with software installation and configuration

    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
    +0.12
    0.5%
    766
    +0.11
    0.5%
    235
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.12
    0.03
    152
    +0.11
    0.03
    365
    +0.10
    0.02
    Negative Logits
     Tone
    -0.95
     Coil
    -0.85
     Emmy
    -0.80
    ONSORED
    -0.80
     Mouth
    -0.79
     Pell
    -0.78
     Clause
    -0.74
     Scare
    -0.73
     Proposition
    -0.73
     Moody
    -0.72
    POSITIVE LOGITS
    tools
    1.35
    manager
    1.25
    guide
    1.25
    scripts
    1.19
    storage
    1.17
    server
    1.14
    sd
    1.14
    utils
    1.12
    cdn
    1.10
    compan
    1.08
    Activations Density 0.117%

    No Known Activations