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

    Neuronpedia

    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. 15742
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and creators of works

    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
    iasm
    -0.84
    zers
    -0.71
    thood
    -0.70
    boxing
    -0.70
    weak
    -0.66
    addons
    -0.64
    udging
    -0.63
    activate
    -0.63
    vin
    -0.63
    wards
    -0.62
    POSITIVE LOGITS
     Jr
    0.94
     Architects
    0.92
     QC
    0.91
     PhD
    0.88
     CFR
    0.83
     aka
    0.82
     who
    0.78
     whose
    0.77
     ISBN
    0.72
     LLC
    0.72
    Activations Density 0.239%

    No Known Activations