© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14580
    Prev
    Next
    INDEX
    Explanations

    instances of text related to withdrawal or removal

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "from" indicating withdrawal or removal

    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
    retty
    -0.78
     teasp
    -0.77
    PRESS
    -0.74
    ratulations
    -0.73
    ascript
    -0.71
    yout
    -0.71
    audi
    -0.70
    leneck
    -0.70
    grain
    -0.68
    Assistant
    -0.68
    POSITIVE LOGITS
     whence
    0.98
     thence
    0.91
     afar
    0.87
     scratch
    0.85
     captivity
    0.79
     Brune
    0.73
     Rav
    0.71
     infancy
    0.69
     Aval
    0.67
     somewhere
    0.67
    Activations Density 0.114%

    No Known Activations