© 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. 13403
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a strong, clear, or extreme contrast

    oai_token-act-pair · gpt-3.5-turbo

    the word "stark" in various contexts indicating sharp contrasts or differences

    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
    phis
    -0.72
    uthor
    -0.67
    ipop
    -0.67
    NetMessage
    -0.65
    PU
    -0.64
    hops
    -0.64
    amins
    -0.64
    uters
    -0.64
    annis
    -0.64
    RAFT
    -0.63
    POSITIVE LOGITS
     contrasts
    1.15
    ly
    0.97
     contrast
    0.97
     stark
    0.88
     naked
    0.83
    itud
    0.82
     contrasting
    0.79
     shifts
    0.78
    est
    0.74
     disson
    0.73
    Activations Density 0.014%

    No Known Activations