© 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. 9-RES-JB
    11. 1002
    Prev
    Next
    INDEX
    Explanations

    patterns related to describing methods, procedures, or approaches

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing methods or manners of doing things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downed
    -0.71
    iage
    -0.69
     raging
    -0.68
     sights
    -0.67
    apsed
    -0.64
     Huge
    -0.61
     newfound
    -0.61
     buzzing
    -0.61
     SOLD
    -0.61
     wandering
    -0.60
    POSITIVE LOGITS
     minimize
    1.03
     maxim
    1.01
     maximize
    0.99
     equitable
    0.98
     minim
    0.96
     conform
    0.93
     preserves
    0.92
     inclusive
    0.91
     sustainable
    0.90
     respectful
    0.89
    Activations Density 0.345%

    No Known Activations