© 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. 20739
    Prev
    Next
    INDEX
    Explanations

    phrases related to science fiction

    oai_token-act-pair · gpt-3.5-turbo

    mentions of science fiction and its subgenres, particularly in relation to entertainment and storytelling

    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
    umm
    -0.92
    enges
    -0.79
    hens
    -0.74
    etsk
    -0.74
    eret
    -0.71
    hap
    -0.68
    etts
    -0.68
    ciating
    -0.67
     Members
    -0.67
    apsed
    -0.67
    POSITIVE LOGITS
     novels
    1.47
     fiction
    1.45
     thriller
    1.35
     novelist
    1.33
     novel
    1.25
     anthology
    1.23
     tropes
    1.16
     genre
    1.14
     flick
    1.08
     films
    1.08
    Activations Density 0.136%

    No Known Activations