© 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 EvalsExportsAPI 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. 3244
    Prev
    Next
    INDEX
    Explanations

    references to a specific character named Peter and other characters interacting with him

    oai_token-act-pair · gpt-3.5-turbo

    characters and their actions within a narrative context

    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
    genre
    -0.76
    ï¸ı
    -0.73
    Trend
    -0.72
     Myanmar
    -0.71
    utterstock
    -0.68
    STEM
    -0.68
    IQ
    -0.67
    Fit
    -0.67
    aic
    -0.66
     ABV
    -0.66
    POSITIVE LOGITS
     disguised
    1.01
     Luffy
    0.93
     convin
    0.93
     unconscious
    0.92
    anwhile
    0.90
     angrily
    0.89
     disgu
    0.88
     imprisoned
    0.87
     kidnapped
    0.87
     reluctantly
    0.86
    Activations Density 0.446%

    No Known Activations