© 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. 23330
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Patrick"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Patrick."

    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
     ACTIONS
    -0.87
     diseng
    -0.71
    )=(
    -0.69
    \-
    -0.68
    âĶĢ
    -0.68
    saf
    -0.67
    iza
    -0.66
     680
    -0.66
    bang
    -0.65
     777
    -0.64
    POSITIVE LOGITS
     Patrick
    3.46
    Patrick
    2.78
    patrick
    1.52
     Patty
    1.52
     Brendan
    1.40
     Keith
    1.38
     Brian
    1.38
     Travis
    1.35
     Patricia
    1.34
     Nicholas
    1.33
    Activations Density 0.016%

    No Known Activations