© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 10144
    Prev
    Next
    INDEX
    Explanations

    phrases related to confessions or discipline

    oai_token-act-pair · gpt-3.5-turbo

    statements of confession or admission of guilt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unison
    -0.73
    agonists
    -0.65
    %%
    -0.64
    oops
    -0.63
    UGC
    -0.63
    è£ħ
    -0.62
    skirts
    -0.62
     Whedon
    -0.61
    choes
    -0.60
    etheless
    -0.60
    POSITIVE LOGITS
     himself
    1.39
     his
    1.14
     Himself
    0.99
    His
    0.92
     ..."
    0.91
    his
    0.90
     [
    0.88
    .''
    0.84
     us
    0.80
     His
    0.80
    Activations Density 0.523%

    No Known Activations