© 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. 4-RES-JB
    11. 1083
    Prev
    Next
    INDEX
    Explanations

    references to the person Richard Dawkins

    oai_token-act-pair · gpt-3.5-turbo

    references to the individuals Richard Dawkins and Davies

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

    No Comments

    Negative Logits
    undai
    -0.69
    iliation
    -0.67
     skelet
    -0.66
     servicing
    -0.66
     joints
    -0.65
    bered
    -0.65
     surgeon
    -0.62
    rian
    -0.61
    venge
    -0.61
    ral
    -0.61
    POSITIVE LOGITS
    sonian
    0.89
    loo
    0.85
    gaard
    0.83
    Discussion
    0.81
    DragonMagazine
    0.81
    yk
    0.79
    hof
    0.79
    atche
    0.76
    itton
    0.75
    pread
    0.74
    Activations Density 0.017%

    No Known Activations