© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16998
    Prev
    Next
    INDEX
    Explanations

    the name "Ryan"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ryan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cane
    -0.81
    iculture
    -0.80
    Enabled
    -0.71
     colonies
    -0.70
     colon
    -0.69
    UME
    -0.67
     beet
    -0.67
     colonial
    -0.66
    icult
    -0.63
    ect
    -0.63
    POSITIVE LOGITS
     Ryan
    3.57
    Ryan
    3.05
     Bryan
    1.44
    ryan
    1.41
     Sean
    1.39
     Craig
    1.36
     Tyler
    1.29
     Cameron
    1.27
     Rooney
    1.27
     Travis
    1.26
    Activations Density 0.019%

    No Known Activations