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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11635
    Prev
    Next
    INDEX
    Explanations

    times and places mentioned in interviews

    oai_token-act-pair · gpt-3.5-turbo

    instances of interviews or discussions occurring in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.78
    rats
    -0.77
    ]=
    -0.70
    TRY
    -0.67
    Results
    -0.67
    Includes
    -0.67
    ãĤ¦ãĤ¹
    -0.65
    Sounds
    -0.64
    Cover
    -0.64
    Join
    -0.63
    POSITIVE LOGITS
     spokesperson
    0.92
     spokesman
    0.90
     however
    0.86
     Mr
    0.86
     Deputy
    0.85
     spokeswoman
    0.83
     Commissioner
    0.82
     Assistant
    0.81
     former
    0.79
     Senator
    0.79
    Activations Density 0.132%

    No Known Activations