© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3868
    Prev
    Next
    INDEX
    Explanations

    words that start with the letter 'w'

    oai_token-act-pair · gpt-3.5-turbo

    the letter "w"

    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
     depri
    -0.75
     deprived
    -0.74
    phy
    -0.71
     succeeding
    -0.71
    egal
    -0.69
    HAEL
    -0.68
    oresc
    -0.67
     culp
    -0.66
    displayText
    -0.66
    pora
    -0.66
    POSITIVE LOGITS
    ither
    1.05
    avy
    0.98
    pn
    0.96
    atson
    0.96
    atts
    0.94
    wn
    0.92
    ithering
    0.90
    itty
    0.88
    irts
    0.88
    avering
    0.88
    Activations Density 0.010%

    No Known Activations