© 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. 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. 3297
    Prev
    Next
    INDEX
    Explanations

    statements of evaluation or judgment

    oai_token-act-pair · gpt-3.5-turbo

    statements of opinion or assertions

    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
    enne
    -0.82
     Remastered
    -0.78
    arella
    -0.76
    ãĤ£
    -0.75
    ventures
    -0.73
    ipl
    -0.71
     Emer
    -0.71
    annabin
    -0.71
    »Ĵ
    -0.70
     Horizons
    -0.69
    POSITIVE LOGITS
     counterproductive
    1.56
     disrespectful
    1.55
     unethical
    1.47
     immoral
    1.42
     irresponsible
    1.41
     unacceptable
    1.39
     hypocritical
    1.35
     insulting
    1.31
     unfair
    1.31
     wasteful
    1.30
    Activations Density 0.242%

    No Known Activations