© 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. 20176
    Prev
    Next
    INDEX
    Explanations

    instances where the word "perhaps" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "perhaps"

    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
    lete
    -0.73
    ocene
    -0.73
    arthed
    -0.72
    tains
    -0.72
    vance
    -0.71
    ulative
    -0.70
    elight
    -0.69
    yers
    -0.68
    eworld
    -0.68
    ved
    -0.67
    POSITIVE LOGITS
     unsurprisingly
    0.80
     "$:/
    0.76
     sensing
    0.75
     unsus
    0.73
     amen
    0.73
     allev
    0.72
     irrit
    0.71
     opio
    0.70
     ironically
    0.70
     occas
    0.68
    Activations Density 0.016%

    No Known Activations