© 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. 0-RES-JB
    11. 1569
    Prev
    Next
    INDEX
    Explanations

    phrases that express doubt or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    negation or terms indicating something is not true or applicable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bow
    -0.64
     yards
    -0.63
     wheel
    -0.62
     leases
    -0.62
     surrounding
    -0.60
     knees
    -0.59
     pal
    -0.59
     hostage
    -0.59
     dream
    -0.57
     handed
    -0.57
    POSITIVE LOGITS
    not
    3.65
    NOT
    2.10
    Not
    1.73
    no
    1.57
    never
    1.53
    notation
    1.42
    rather
    1.38
    nothing
    1.38
     NOT
    1.31
    now
    1.29
    Activations Density 0.006%

    No Known Activations