© 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. 3-RES-JB
    11. 13575
    Prev
    Next
    INDEX
    Explanations

    references to specific decades using a numerical format

    oai_token-act-pair · gpt-3.5-turbo

    mentions of decades, particularly the 1950s, 1960s, 1970s, and 1980s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Phys
    -0.82
    è»
    -0.72
    acts
    -0.69
    ãĥ¤
    -0.67
    ournals
    -0.67
    Dialogue
    -0.67
    OVER
    -0.67
    imentary
    -0.65
    ibrary
    -0.64
    SET
    -0.64
    POSITIVE LOGITS
    ixties
    0.94
     Era
    0.93
     onwards
    0.91
     onward
    0.89
     era
    0.86
     Jah
    0.82
    outhern
    0.77
    enegger
    0.77
    ayers
    0.76
     century
    0.71
    Activations Density 0.085%

    No Known Activations