© 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. 9558
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly focusing on the name "Sophie"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sophie" and related proper nouns

    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
    hips
    -0.86
    ees
    -0.83
    inez
    -0.81
    iggurat
    -0.78
    itated
    -0.76
    ports
    -0.75
    redo
    -0.73
    herty
    -0.73
    orne
    -0.72
    ulhu
    -0.72
    POSITIVE LOGITS
     Sophie
    0.84
     Choice
    0.80
    oleon
    0.79
    isters
    0.73
    atis
    0.72
     Vie
    0.69
    ISM
    0.68
     Breaker
    0.68
     Gö
    0.67
     Sasha
    0.67
    Activations Density 0.022%

    No Known Activations