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. 9-RES-JB
    6. 1131
    Prev
    Next
    INDEX
    Explanations

    financial terms or mentions of transactions

    oai_token-act-pair · gpt-3.5-turbo

    commas, especially those used in lists or to separate clauses in a sentence.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    instances of the phrase "aside from" or "in addition to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cko
    -0.76
    èĢħ
    -0.75
    Switch
    -0.70
    onym
    -0.69
    ilial
    -0.68
    nai
    -0.68
    arch
    -0.66
    ione
    -0.65
    eker
    -0.65
    jri
    -0.64
    POSITIVE LOGITS
     there
    0.99
     moreover
    0.84
     however
    0.80
     which
    0.80
    there
    0.79
     besides
    0.77
     another
    0.75
     meanwhile
    0.72
    Secondly
    0.68
     innumerable
    0.67
    Activations Density 0.124%

    No Known Activations