© 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. 0-RES-JB
    11. 20017
    Prev
    Next
    INDEX
    Explanations

    names related to "Harvey"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Har"

    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
     Sloven
    -0.71
     Yugoslav
    -0.71
     Slovenia
    -0.69
     passport
    -0.69
     Caucasian
    -0.68
     sketches
    -0.67
     sol
    -0.64
     Vo
    -0.64
     ski
    -0.64
     Rost
    -0.64
    POSITIVE LOGITS
    Har
    3.94
    har
    1.92
     Har
    1.90
     HAR
    1.74
     Harper
    1.67
     Harvey
    1.39
     har
    1.37
     Haram
    1.33
    Gar
    1.26
    Harris
    1.26
    Activations Density 0.016%

    No Known Activations