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. 3406
    Prev
    Next
    INDEX
    Explanations

    periods used with additional separator characters like commas and colons

    oai_token-act-pair · gpt-3.5-turbo

    statements that reflect assertions or conclusions about societal structures

    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
    ascus
    -0.86
     earthqu
    -0.84
    ributes
    -0.78
     advis
    -0.76
     escort
    -0.74
     haul
    -0.74
     requested
    -0.74
     scheduled
    -0.74
    oshenko
    -0.72
     billed
    -0.70
    POSITIVE LOGITS
     Hence
    1.53
     Therefore
    1.48
     Consequently
    1.46
     Whereas
    1.45
     Thus
    1.44
     Moreover
    1.34
     Accordingly
    1.34
     Conversely
    1.26
     Furthermore
    1.24
     Whether
    1.23
    Activations Density 0.527%

    No Known Activations