© 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. 1-RES-JB
    6. 8642
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific individuals named "Hayden."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly "Hayden," "McKenzie," and "Petraeus."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alions
    -0.79
    clerosis
    -0.74
    ramid
    -0.72
    NetMessage
    -0.69
    htaking
    -0.69
    unders
    -0.68
    icably
    -0.67
    inal
    -0.67
    pperc
    -0.67
    berman
    -0.66
    POSITIVE LOGITS
     Hayden
    0.98
     Christensen
    0.80
    bryce
    0.71
    renheit
    0.70
     Petraeus
    0.70
    flower
    0.69
    ategory
    0.68
    burgh
    0.68
    film
    0.68
    20439
    0.67
    Activations Density 0.009%

    No Known Activations