© 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. 2-RES-JB
    11. 8433
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific character named "Boy"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Boy" in various contexts, indicating a focus on themes or narratives involving young males

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -1.17
    aukee
    -0.85
     podium
    -0.78
    incinn
    -0.72
    ickr
    -0.72
     equilibrium
    -0.71
     clutter
    -0.70
     inbox
    -0.70
     fabrication
    -0.70
    insula
    -0.69
    POSITIVE LOGITS
    friend
    1.38
    boy
    1.20
     Scouts
    1.18
     Boy
    1.14
    boys
    1.12
    cott
    1.09
    hood
    1.06
    Boy
    1.04
     Scout
    1.02
    Girl
    0.97
    Activations Density 0.008%

    No Known Activations