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. 8-RES-JB
    6. 18320
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    calls to action typically associated with hyperlinks or clickable content

    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
    ãĥ£
    -0.68
    opoulos
    -0.64
    Ts
    -0.61
     quot
    -0.59
     transpl
    -0.58
     sugars
    -0.57
    pects
    -0.57
    meat
    -0.57
     warranties
    -0.56
     tones
    -0.56
    POSITIVE LOGITS
     LINK
    0.79
    tics
    0.75
     Submit
    0.75
    tical
    0.74
     Wiki
    0.73
     âĢº
    0.72
     [+]
    0.72
     Oops
    0.70
    umbnail
    0.68
    abouts
    0.67
    Activations Density 0.019%

    No Known Activations