© 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. 1-RES-JB
    11. 20822
    Prev
    Next
    INDEX
    Explanations

    references to locations or directional guidance

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Way."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rador
    -0.85
    ioch
    -0.75
    uster
    -0.73
    ĸļ
    -0.71
     quo
    -0.70
     prosec
    -0.70
     sugg
    -0.69
    asts
    -0.69
    usters
    -0.65
    essions
    -0.65
    POSITIVE LOGITS
    fare
    1.32
    ward
    1.12
    Way
    1.12
    way
    1.09
     Way
    0.97
    WARD
    0.95
    Forward
    0.89
     WAY
    0.86
     Forward
    0.84
    ways
    0.83
    Activations Density 0.007%

    No Known Activations