© 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 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. 6485
    Prev
    Next
    INDEX
    Explanations

    elements indicating structure and logic in written sequences

    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
    165
    +0.13
    0.6%
    313
    +0.10
    0.5%
    750
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.07
    289
    +0.10
    0.03
    699
    +0.09
    0.04
    Negative Logits
     grounding
    -0.70
     ner
    -0.70
     ideal
    -0.69
     artificial
    -0.69
     mechanic
    -0.68
     schematic
    -0.67
     goggles
    -0.67
     heroism
    -0.66
     realism
    -0.66
     electromagnetic
    -0.65
    POSITIVE LOGITS
    /$
    1.23
    ${
    1.14
    $
    1.13
     $_
    1.11
    ($
    1.10
    -$
    1.09
     "$
    1.08
    $,
    1.08
    =$
    1.07
    .$
    1.04
    Activations Density 0.414%

    No Known Activations