© 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. 6-RES-JB
    11. 9405
    Prev
    Next
    INDEX
    Explanations

    references to the horror genre

    oai_token-act-pair · gpt-3.5-turbo

    references to the horror genre

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.78
    dated
    -0.76
    cially
    -0.75
    holder
    -0.70
    lease
    -0.68
    apsed
    -0.68
    nington
    -0.67
    ients
    -0.65
    lement
    -0.64
    ilib
    -0.64
    POSITIVE LOGITS
     Horror
    1.18
     horror
    0.96
    Alien
    0.82
    crow
    0.79
     flick
    0.79
    mong
    0.78
     Cthulhu
    0.78
    genre
    0.78
     movies
    0.76
     crawl
    0.76
    Activations Density 0.034%

    No Known Activations