© 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. 9-RES-JB
    11. 15361
    Prev
    Next
    INDEX
    Explanations

    requests or invitations for someone to come or visit a place

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "come."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asio
    -0.74
    culus
    -0.72
    chance
    -0.70
    versible
    -0.69
    İĭ
    -0.69
    alde
    -0.68
    orst
    -0.68
    nesota
    -0.67
    ciples
    -0.65
    ruff
    -0.64
    POSITIVE LOGITS
     forth
    1.09
     ashore
    1.01
     hither
    1.01
     aboard
    0.91
     undone
    0.87
     alive
    0.87
     forward
    0.87
     knocking
    0.87
     back
    0.82
     INTO
    0.81
    Activations Density 0.058%

    No Known Activations