© 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. 8-RES-JB
    11. 3068
    Prev
    Next
    INDEX
    Explanations

    questions about identity or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    subjects of inquiry or investigation expressed through the word "who."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    framework
    -0.77
    requ
    -0.69
    ooters
    -0.67
    stantial
    -0.64
    irth
    -0.63
     Candle
    -0.63
    vity
    -0.63
    naissance
    -0.62
     externalToEVAOnly
    -0.62
     Supplemental
    -0.61
    POSITIVE LOGITS
     infiltrated
    0.82
     benefited
    0.80
    afort
    0.80
     whom
    0.78
     inhab
    0.73
     footing
    0.73
     owns
    0.72
     deceived
    0.71
     orchestr
    0.70
     filib
    0.69
    Activations Density 0.082%

    No Known Activations