© 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. 7-RES-JB
    11. 21198
    Prev
    Next
    INDEX
    Explanations

    names of roles or characters in various productions

    oai_token-act-pair · gpt-3.5-turbo

    references to roles or performances in film and television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.95
    vier
    -0.80
    sonian
    -0.71
    ensable
    -0.67
    tenance
    -0.66
    cling
    -0.65
     newsletters
    -0.65
     Gallup
    -0.63
    pex
    -0.61
    foundation
    -0.61
    POSITIVE LOGITS
     actress
    0.93
    acters
    0.93
     actor
    0.87
    wright
    0.85
     portraying
    0.85
     portrayal
    0.84
     audition
    0.81
     actresses
    0.79
     portray
    0.78
     Actress
    0.78
    Activations Density 0.098%

    No Known Activations