© 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. 24056
    Prev
    Next
    INDEX
    Explanations

    the word "behold" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "behold" indicating surprise or attention

    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
     MacArthur
    -0.75
     Atkinson
    -0.67
     interrogation
    -0.66
     medic
    -0.63
     Aberdeen
    -0.62
    cussion
    -0.61
     Hiroshima
    -0.61
     Scotia
    -0.60
    ucc
    -0.60
     quarantine
    -0.60
    POSITIVE LOGITS
     behold
    1.57
    entimes
    1.22
    ardless
    0.98
    masters
    0.93
    ers
    0.89
    iful
    0.88
    erers
    0.85
    enance
    0.82
    elines
    0.81
    icult
    0.81
    Activations Density 0.009%

    No Known Activations