© 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. 20861
    Prev
    Next
    INDEX
    Explanations

    words related to science fiction and fantasy

    oai_token-act-pair · gpt-3.5-turbo

    references to science fiction

    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
     Bott
    -0.67
     Burr
    -0.67
     Pearl
    -0.66
     Whites
    -0.64
     Cups
    -0.64
     majorities
    -0.64
     Dign
    -0.64
     Bennett
    -0.63
     Marqu
    -0.63
     Kau
    -0.62
    POSITIVE LOGITS
    fi
    1.47
    Fi
    1.14
    sci
    1.06
    fiction
    1.05
    tech
    0.96
    ê
    0.91
     fi
    0.85
    terrorism
    0.84
    Tech
    0.84
    friendly
    0.83
    Activations Density 0.032%

    No Known Activations