© 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. 7-RES-JB
    11. 17205
    Prev
    Next
    INDEX
    Explanations

    phrases related to political messages displayed through signs or stickers

    oai_token-act-pair · gpt-3.5-turbo

    quotations and slogans related to social justice issues

    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
     stride
    -0.78
     term
    -0.73
     blush
    -0.72
     chunk
    -0.72
     theoret
    -0.71
     scales
    -0.71
     frame
    -0.71
     topic
    -0.71
     predicate
    -0.69
     subject
    -0.69
    POSITIVE LOGITS
    RIP
    1.12
    Dear
    1.07
     Goodbye
    1.01
    Congratulations
    0.99
    $$$$
    0.97
    Tomorrow
    0.94
    Eat
    0.92
    ESCO
    0.91
    LO
    0.91
    ãģĤ
    0.89
    Activations Density 0.199%

    No Known Activations