© 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. 7-RES-JB
    11. 1489
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    statements reflecting certainty or awareness

    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
    isco
    -0.91
    onding
    -0.78
    issance
    -0.75
    aez
    -0.72
    acies
    -0.71
     sidx
    -0.71
    aukee
    -0.69
    gencies
    -0.69
    erva
    -0.67
    taboola
    -0.67
    POSITIVE LOGITS
     firsthand
    1.01
     how
    0.82
     exactly
    0.79
     nothing
    0.77
     plenty
    0.71
    nothing
    0.71
     what
    0.71
    ledged
    0.70
     personally
    0.68
     beforehand
    0.66
    Activations Density 0.051%

    No Known Activations