© 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. 8-RES-JB
    11. 24490
    Prev
    Next
    INDEX
    Explanations

    statements or opinions given by individuals

    oai_token-act-pair · gpt-3.5-turbo

    quotes and statements made by various political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.82
     Cf
    -0.81
    them
    -0.66
    _-
    -0.66
    \/\/
    -0.66
    wk
    -0.65
    Pg
    -0.64
    ////////////////////////////////
    -0.64
    ItemThumbnailImage
    -0.64
     kcal
    -0.62
    POSITIVE LOGITS
     embattled
    0.77
     Donald
    0.75
     homosexuality
    0.73
     passionately
    0.70
    iths
    0.69
     Scientology
    0.67
     Christianity
    0.66
     blaming
    0.64
    ylum
    0.63
     constitu
    0.63
    Activations Density 0.265%

    No Known Activations