Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6668
    Prev
    Next
    INDEX
    Explanations

    articles or news items about specific topics or keywords

    oai_token-act-pair · gpt-3.5-turbo

    URLs or website references in the text

    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
     Surprise
    -0.67
     Goo
    -0.66
     Belt
    -0.64
     Parenthood
    -0.64
     Athletic
    -0.63
     Bradley
    -0.62
     compounded
    -0.62
     Pupp
    -0.61
     Daly
    -0.61
     Cotton
    -0.61
    POSITIVE LOGITS
    /)
    1.27
    /,
    1.25
    /?
    1.20
    /.
    1.09
    /#
    1.08
    /_
    1.03
    _
    1.03
    _-_
    0.96
    guide
    0.95
    php
    0.94
    Activations Density 0.098%

    No Known Activations