© 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. 11-RES-JB
    11. 10285
    Prev
    Next
    INDEX
    Explanations

    phrases related to online documents like HTML files and PDFs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the period punctuation

    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
     sexism
    -0.70
     literacy
    -0.68
     induct
    -0.68
     mentors
    -0.68
     lockout
    -0.66
     bonuses
    -0.65
     defects
    -0.65
     clocks
    -0.65
     portraits
    -0.63
     ages
    -0.63
    POSITIVE LOGITS
    html
    2.13
    htm
    2.02
    aspx
    1.92
    php
    1.74
    pdf
    1.65
    asp
    1.61
    jpg
    1.52
    png
    1.42
    gif
    1.42
    cf
    1.40
    Activations Density 0.036%

    No Known Activations