© 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. 9373
    Prev
    Next
    INDEX
    Explanations

    demonstrative terms followed by information or facts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Here" followed by additional information or context

    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
    omedical
    -0.65
    omore
    -0.63
    Zen
    -0.62
     grace
    -0.60
    Shape
    -0.58
     hygiene
    -0.57
    offensive
    -0.55
     LSD
    -0.55
    ped
    -0.55
    ces
    -0.54
    POSITIVE LOGITS
    tics
    1.07
    here
    1.03
    abouts
    0.97
    tical
    0.94
    tic
    0.94
     Transcript
    0.89
     newsp
    0.89
    ford
    0.78
     Comes
    0.78
     Here
    0.73
    Activations Density 0.014%

    No Known Activations