© 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. 24195
    Prev
    Next
    INDEX
    Explanations

    instances where the word "testimony" appears

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "testimony."

    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
    yright
    -0.75
     Pixie
    -0.74
     Chop
    -0.65
    ordinate
    -0.65
    animate
    -0.64
     Pis
    -0.64
    rave
    -0.63
    FFFF
    -0.63
    erm
    -0.61
    aged
    -0.60
    POSITIVE LOGITS
     testimony
    1.40
     testimonies
    1.33
    imony
    1.08
     witnesses
    0.99
     testify
    0.97
     testifying
    0.95
     witness
    0.90
     testified
    0.86
     hearings
    0.84
    reports
    0.80
    Activations Density 0.007%

    No Known Activations