© 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. 4-RES-JB
    11. 10117
    Prev
    Next
    INDEX
    Explanations

    references to the word "Lincoln."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Lincoln."

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

    No Comments

    Negative Logits
     Flavoring
    -0.96
    PDATE
    -0.75
    Org
    -0.67
     scant
    -0.67
     exaggeration
    -0.66
    VALUE
    -0.66
     constitu
    -0.66
    -----------
    -0.66
    ++++++++++++++++
    -0.63
    NetMessage
    -0.63
    POSITIVE LOGITS
    shire
    1.57
    incoln
    0.99
     Lincoln
    0.92
    hurst
    0.89
     Memorial
    0.83
    gren
    0.80
     Park
    0.79
    dale
    0.74
     Cooper
    0.74
    sson
    0.73
    Activations Density 0.010%

    No Known Activations