© 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. 2-RES-JB
    11. 12236
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Henderson."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Henderson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.82
    opsy
    -0.78
    EP
    -0.70
    cing
    -0.66
    urity
    -0.66
    perture
    -0.64
    URI
    -0.63
    haps
    -0.63
    ãĥ¯
    -0.63
    onomy
    -0.63
    POSITIVE LOGITS
     Henderson
    1.24
     Alvarez
    0.77
    ville
    0.77
    ega
    0.76
     Hendricks
    0.75
     Reeves
    0.70
    ragon
    0.69
    endish
    0.67
     bri
    0.66
    eming
    0.66
    Activations Density 0.013%

    No Known Activations