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. 6-RES-JB
    6. 21079
    Prev
    Next
    INDEX
    Explanations

    web-related tokens such as sources, widgets, campaigns, and medium

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to web analytics and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -0.79
    natureconservancy
    -0.78
     scrut
    -0.73
    é¾įå
    -0.70
    xus
    -0.68
    eas
    -0.68
    Æ
    -0.67
    ecause
    -0.67
     arsen
    -0.66
     belts
    -0.65
    POSITIVE LOGITS
    _
    1.14
    __
    1.01
    ()
    0.85
    _.
    0.75
    _-_
    0.74
    llor
    0.73
    ___
    0.72
    ._
    0.69
    ption
    0.67
    oca
    0.66
    Activations Density 0.073%

    No Known Activations