© 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. 8-RES-JB
    6. 7775
    Prev
    Next
    INDEX
    Explanations

    website urls at the end of sentences prompting the reader to share or read a story

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating options or alternatives

    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
    hower
    -0.83
    steen
    -0.73
    hol
    -0.67
    ouls
    -0.66
    ngth
    -0.64
    ļé
    -0.62
    matter
    -0.60
    puter
    -0.59
    atari
    -0.59
    natureconservancy
    -0.58
    POSITIVE LOGITS
     Share
    0.68
     Submit
    0.66
     Format
    0.65
     subscribe
    0.65
     Paste
    0.64
    ANGE
    0.63
     hear
    0.63
     Comment
    0.63
    yrics
    0.63
    leans
    0.62
    Activations Density 0.038%

    No Known Activations