© 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. 976
    Prev
    Next
    INDEX
    Explanations

    the surname "Hopkins"

    oai_token-act-pair · gpt-4-turbo

    proper nouns related to "Hopkins"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Hopkins" and related references

    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
    cing
    -0.82
    gered
    -0.82
    razil
    -0.71
    ãĥł
    -0.70
     deleting
    -0.70
    semble
    -0.65
     Saddam
    -0.65
     Savior
    -0.64
    $$$$
    -0.63
     redistributed
    -0.62
    POSITIVE LOGITS
     Hopkins
    1.37
    kinson
    0.87
    nown
    0.86
    kins
    0.86
    ley
    0.84
    lett
    0.81
    worth
    0.80
    bay
    0.79
    erenn
    0.79
    leys
    0.78
    Activations Density 0.006%

    No Known Activations