© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7144
    Prev
    Next
    INDEX
    Explanations

    formatting errors in input fields, specifically related to email addresses

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods indicating the end of sentences

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

    No Comments

    Negative Logits
     oun
    -0.78
     brut
    -0.76
     additive
    -0.73
     homebrew
    -0.72
     bos
    -0.71
     gobl
    -0.69
     manif
    -0.69
     playable
    -0.69
    ouf
    -0.69
    anus
    -0.68
    POSITIVE LOGITS
     Please
    1.07
    php
    0.95
    dll
    0.93
    html
    0.93
    tumblr
    0.90
    google
    0.89
    push
    0.87
    jpg
    0.87
    aspx
    0.86
     However
    0.86
    Activations Density 0.195%

    No Known Activations