© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 9891
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sentence-ending punctuation period

    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
     coord
    -0.72
     solitude
    -0.67
     nodd
    -0.64
     independ
    -0.63
     defe
    -0.63
     fung
    -0.63
     defaults
    -0.63
     monopol
    -0.62
     moderation
    -0.62
     facult
    -0.62
    POSITIVE LOGITS
     Specifically
    1.16
     Included
    0.94
     Instead
    0.92
     Additionally
    0.91
     However
    0.90
     Though
    0.89
     Previously
    0.87
     While
    0.87
     Unlike
    0.86
     According
    0.86
    Activations Density 0.386%

    No Known Activations