Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9284
    Prev
    Next
    INDEX
    Explanations

    dates expressed in the format of "Month - Number."

    oai_token-act-pair · gpt-3.5-turbo

    dates and times associated with events

    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
     pse
    -0.80
     subscript
    -0.76
    attribute
    -0.75
    Versions
    -0.70
    ¥ŀ
    -0.70
    iannopoulos
    -0.70
     tremend
    -0.69
    xual
    -0.69
    oglobin
    -0.67
     suscept
    -0.65
    POSITIVE LOGITS
     Seattle
    1.42
     Atlanta
    1.39
     Portland
    1.35
     Honolulu
    1.34
     Chicago
    1.34
     Pittsburgh
    1.34
     Philadelphia
    1.32
     Charleston
    1.31
     Los
    1.30
     Denver
    1.29
    Activations Density 0.114%

    No Known Activations