© 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. 10-RES_POST_32K-OAI
    11. 28116
    Prev
    Next
    INDEX
    Explanations

    sequences or codes related to data logs or files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    566
    +0.11
    0.5%
    479
    +0.10
    0.5%
    516
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.11
    0.01
    106
    +0.10
    0.01
    314
    +0.10
    -0.00
    Negative Logits
    merce
    -1.07
    ror
    -0.91
    les
    -0.89
    ilities
    -0.89
    ulus
    -0.89
    otrop
    -0.89
    ulas
    -0.88
    imus
    -0.86
    ometry
    -0.86
    rolet
    -0.85
    POSITIVE LOGITS
    VD
    1.24
    TPS
    1.09
    GO
    1.09
    OOD
    1.07
    AIR
    1.07
    UE
    1.06
    DS
    0.99
    GS
    0.98
    PK
    0.97
    AK
    0.97
    Activations Density 0.065%

    No Known Activations