© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28873
    Prev
    Next
    INDEX
    Explanations

    interactions that involve questioning or asking for information

    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
    610
    +0.09
    0.4%
    373
    +0.09
    0.4%
    251
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.09
    0.03
    543
    +0.09
    0.10
    669
    +0.09
    0.13
    Negative Logits
    Magikarp
    -0.67
    yip
    -0.63
    çīĪ
    -0.63
    rahim
    -0.62
    ãĥ¯
    -0.62
    rencies
    -0.60
    sov
    -0.60
    cipled
    -0.59
    anus
    -0.58
    oÄŁ
    -0.58
    POSITIVE LOGITS
     her
    2.63
     herself
    2.60
     she
    2.46
    She
    2.29
     hers
    2.25
    she
    2.20
     She
    2.11
    Her
    2.04
     SHE
    1.98
     Her
    1.81
    Activations Density 24.196%

    No Known Activations