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. 16349
    Prev
    Next
    INDEX
    Explanations

    financial terminology and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases pertaining to identification and sources of evidence

    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
    estyles
    -0.89
     preview
    -0.78
    igr
    -0.67
    eah
    -0.67
    estyle
    -0.65
    resp
    -0.64
    isec
    -0.64
    omination
    -0.64
    arnaev
    -0.64
    Reply
    -0.63
    POSITIVE LOGITS
     Cosponsors
    0.92
     namely
    0.70
     intangible
    0.69
     CGI
    0.65
     petroleum
    0.64
     pus
    0.64
     Qualcomm
    0.62
    ierrez
    0.62
    specified
    0.62
     iTunes
    0.61
    Activations Density 0.566%

    No Known Activations