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. 7-RES-JB
    6. 18437
    Prev
    Next
    INDEX
    Explanations

    instances of speaking or giving speeches

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Speaking" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.79
    ascade
    -0.74
    involved
    -0.73
    aden
    -0.72
    jer
    -0.71
    jl
    -0.69
    ======
    -0.68
    @#&
    -0.68
    version
    -0.68
    ~~~~~~~~
    -0.68
    POSITIVE LOGITS
     engagements
    0.77
     aloud
    0.74
     apart
    0.71
     Pitch
    0.71
     anonymously
    0.71
     excerpts
    0.69
     spoke
    0.68
     charism
    0.68
     fluent
    0.66
     frankly
    0.65
    Activations Density 0.026%

    No Known Activations