© 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. 13101
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'sole.'

    oai_token-act-pair · gpt-3.5-turbo

    the word "sole" indicating singularity or exclusivity

    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
    naires
    -0.74
    enegger
    -0.74
     Caf
    -0.73
    CDC
    -0.73
     Machines
    -0.72
     horm
    -0.71
     MacArthur
    -0.68
     Extrem
    -0.68
     Depression
    -0.65
    icz
    -0.64
    POSITIVE LOGITS
     propriet
    1.08
     sole
    1.03
    isode
    0.82
    mn
    0.81
    toe
    0.79
     exception
    0.78
    teenth
    0.76
    vent
    0.74
    kus
    0.74
     purpose
    0.73
    Activations Density 0.007%

    No Known Activations