© 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. 0-RES-JB
    11. 6251
    Prev
    Next
    INDEX
    Explanations

    ways or methods of doing something

    oai_token-act-pair · gpt-3.5-turbo

    references to methods or approaches for achieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ney
    -0.67
    Ã
    -0.62
    brance
    -0.61
    ensis
    -0.59
    average
    -0.59
    ome
    -0.59
    tex
    -0.59
    amine
    -0.58
    1000
    -0.58
    \'
    -0.56
    POSITIVE LOGITS
     ways
    3.87
     Ways
    2.16
     way
    1.56
     WAY
    1.47
     methods
    1.36
     reasons
    1.29
     respects
    1.27
     manners
    1.27
     avenues
    1.25
     strategies
    1.22
    Activations Density 0.021%

    No Known Activations