© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3677
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the name "Lyle."

    oai_token-act-pair · gpt-3.5-turbo

    names associated with individuals or characters

    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
    arius
    -0.80
     antioxid
    -0.79
    Angelo
    -0.76
    ging
    -0.69
    kaya
    -0.66
    duty
    -0.66
     Gujar
    -0.66
    Va
    -0.65
    ENTS
    -0.63
    ues
    -0.62
    POSITIVE LOGITS
    phrine
    0.92
    ttes
    0.88
    yles
    0.79
    ffe
    0.79
    edia
    0.75
    uffs
    0.73
    braska
    0.73
    aundering
    0.72
    apons
    0.72
    thur
    0.71
    Activations Density 0.031%

    No Known Activations