© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12876
    Prev
    Next
    INDEX
    Explanations

    confirmation-related terms or activities, such as confirmation hearings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confirmation."

    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
    uld
    -0.80
    ÃŁ
    -0.76
    INK
    -0.73
     ILCS
    -0.71
    @#&
    -0.71
    κ
    -0.69
    otrop
    -0.67
     Extrem
    -0.67
    ε
    -0.67
    verning
    -0.66
    POSITIVE LOGITS
    irmation
    1.63
     confirmation
    1.44
    irming
    1.01
     confirm
    0.95
    irmed
    0.90
     appointment
    0.88
     confirming
    0.85
     indication
    0.82
     affirmation
    0.81
    irms
    0.81
    Activations Density 0.006%

    No Known Activations