© 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. 7-RES-JB
    11. 13514
    Prev
    Next
    INDEX
    Explanations

    the word "Tyson."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Tyson."

    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
    liest
    -0.68
    nia
    -0.68
    fully
    -0.67
    gery
    -0.66
    ======
    -0.66
    fulness
    -0.66
    gress
    -0.66
    cano
    -0.65
    tc
    -0.65
    umen
    -0.65
    POSITIVE LOGITS
     Foods
    0.87
     Kor
    0.75
    ertodd
    0.70
     Kov
    0.69
    imov
    0.68
     Simmons
    0.68
    fman
    0.67
    ocrates
    0.65
    sov
    0.65
     Ascend
    0.64
    Activations Density 0.089%

    No Known Activations