© 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. 9485
    Prev
    Next
    INDEX
    Explanations

    words related to the color green

    oai_token-act-pair · gpt-3.5-turbo

    references to the color green

    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
    ̶
    -0.82
    ebin
    -0.77
    ROR
    -0.76
    hematic
    -0.67
    rators
    -0.67
    orically
    -0.65
    gerald
    -0.63
    rator
    -0.63
    DCS
    -0.62
    itars
    -0.62
    POSITIVE LOGITS
     green
    1.16
    green
    1.09
    grass
    0.96
    leaf
    0.94
    peace
    0.91
     GREEN
    0.87
    Green
    0.85
     grass
    0.84
    wyn
    0.84
    GREEN
    0.83
    Activations Density 0.010%

    No Known Activations