© 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. 8025
    Prev
    Next
    INDEX
    Explanations

    symbols, mathematical expressions, and structural elements in data

    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
    265
    +0.11
    0.5%
    547
    +0.10
    0.5%
    483
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.11
    678
    +0.10
    0.06
    701
    +0.09
    0.04
    Negative Logits
    API
    -0.83
    Bridge
    -0.82
    SPONSORED
    -0.82
    NBA
    -0.81
    ASC
    -0.78
    European
    -0.77
    URL
    -0.77
    opian
    -0.77
    Revolution
    -0.77
    Unity
    -0.77
    POSITIVE LOGITS
     q
    1.46
     h
    1.34
     s
    1.31
     k
    1.31
     ml
    1.30
     y
    1.28
     c
    1.27
     d
    1.25
     t
    1.25
     u
    1.25
    Activations Density 2.493%

    No Known Activations