© 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. 7357
    Prev
    Next
    INDEX
    Explanations

    contractions with "not"

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of denial

    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
    Site
    -0.71
    ancer
    -0.69
    éĥ
    -0.68
     Inventory
    -0.67
    eur
    -0.65
    inav
    -0.64
    bard
    -0.64
     Presence
    -0.63
    amer
    -0.63
     Publications
    -0.63
    POSITIVE LOGITS
     necessarily
    1.12
    icably
    1.05
     bother
    0.99
     exactly
    0.97
    epad
    0.93
    icable
    0.92
     hesitate
    0.86
    urtles
    0.83
     quite
    0.83
     gonna
    0.83
    Activations Density 0.085%

    No Known Activations