© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26547
    Prev
    Next
    INDEX
    Explanations

    instances of negative aspects or criticisms

    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
    314
    +0.19
    0.9%
    627
    +0.11
    0.5%
    172
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.19
    0.00
    627
    +0.11
    0.02
    152
    +0.10
    0.03
    Negative Logits
     bounce
    -0.80
     breathing
    -0.80
     square
    -0.80
     Carnegie
    -0.79
     contempor
    -0.77
     caution
    -0.74
     hiber
    -0.70
     sep
    -0.68
     cler
    -0.68
     sooner
    -0.66
    POSITIVE LOGITS
    LIB
    1.23
    II
    1.23
    UX
    1.21
    STD
    1.19
    III
    1.18
    GO
    1.18
    FM
    1.18
    RW
    1.18
    DL
    1.18
    ARS
    1.17
    Activations Density 0.201%

    No Known Activations