© 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. 10-RES-JB
    11. 12272
    Prev
    Next
    INDEX
    Explanations

    references to the name "Derrick" at varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    referenced names, particularly focusing on individuals named Derrick or Christina

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imately
    -0.85
    rounder
    -0.70
     fragmentation
    -0.65
    iol
    -0.63
    matically
    -0.62
    berman
    -0.62
    PLIED
    -0.62
    atically
    -0.62
    atic
    -0.61
     Kinnikuman
    -0.61
    POSITIVE LOGITS
    ensen
    0.97
     Jensen
    0.79
    quel
    0.77
    eger
    0.70
     Fiorina
    0.70
    endant
    0.69
    idered
    0.68
    essors
    0.68
    cies
    0.68
    ening
    0.68
    Activations Density 0.075%

    No Known Activations