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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 3546
    Prev
    Next
    INDEX
    Explanations

    words related to natural fibers

    oai_token-act-pair · gpt-3.5-turbo

    references to resources or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tart
    -0.64
     gob
    -0.60
     BI
    -0.58
     today
    -0.58
     slang
    -0.58
     sneaking
    -0.56
     Prophet
    -0.56
     sneak
    -0.56
     differential
    -0.55
     incorporating
    -0.55
    POSITIVE LOGITS
    res
    4.42
    RES
    1.82
    re
    1.76
    Res
    1.75
    resh
    1.72
    resa
    1.55
    resp
    1.49
    rez
    1.43
    rest
    1.41
    ren
    1.39
    Activations Density 0.009%

    No Known Activations