© 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. 1-RES-JB
    11. 24109
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the location "Hamilton"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "Hamilton"

    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
    vg
    -0.81
    asel
    -0.75
    ramid
    -0.74
    ========
    -0.73
    ============
    -0.72
    scription
    -0.71
    lect
    -0.70
    ERAL
    -0.69
    vana
    -0.69
    ======
    -0.66
    POSITIVE LOGITS
     Hamilton
    1.16
    Hamilton
    1.15
     resil
    0.87
    pton
    0.85
    ipeg
    0.81
     McMaster
    0.76
    igon
    0.76
    enburg
    0.74
     contrace
    0.73
    igans
    0.72
    Activations Density 0.010%

    No Known Activations