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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20624
    Prev
    Next
    INDEX
    Explanations

    contractions and negations

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases indicating inability or lack of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esting
    -0.63
    farious
    -0.63
     Appears
    -0.62
    nis
    -0.61
     Matters
    -0.61
     Called
    -0.60
    isible
    -0.59
     STATS
    -0.59
    plates
    -0.58
    amy
    -0.58
    POSITIVE LOGITS
     afford
    1.02
     conce
    0.81
     foresee
    0.79
     feas
    0.78
    cffffcc
    0.77
     convince
    0.76
     possibly
    0.76
     muster
    0.75
     conceive
    0.75
     predict
    0.74
    Activations Density 0.103%

    No Known Activations