© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 20160
    Prev
    Next
    INDEX
    Explanations

    words with special symbols resembling text formatting used incorrectly, possibly a parsing error

    oai_token-act-pair · gpt-3.5-turbo

    numerical data points or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scept
    -0.75
     maths
    -0.70
     civilisation
    -0.66
     temptation
    -0.66
     citiz
    -0.64
     practise
    -0.63
     humour
    -0.63
     obscurity
    -0.61
     ageing
    -0.61
     torture
    -0.61
    POSITIVE LOGITS
    Tickets
    0.88
    PHOTOS
    0.87
    Prior
    0.86
    apeake
    0.83
    Executive
    0.82
    rawdownloadcloneembedreportprint
    0.76
    RELATED
    0.75
    Forward
    0.73
    Notable
    0.70
    Statement
    0.69
    Activations Density 0.478%

    No Known Activations