© 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. 23838
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or awareness

    oai_token-act-pair · gpt-3.5-turbo

    phrases asserting common knowledge or consensus

    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
    pex
    -0.88
    ermanent
    -0.78
    erva
    -0.76
    osi
    -0.73
    cific
    -0.73
    rentice
    -0.73
    onial
    -0.71
    ĪĴ
    -0.71
    oshenko
    -0.71
    cohol
    -0.70
    POSITIVE LOGITS
    ledge
    0.89
    ledged
    0.87
     how
    0.84
     beforehand
    0.74
    lege
    0.71
    ariat
    0.71
     nothing
    0.69
    л
    0.68
    nothing
    0.67
     why
    0.66
    Activations Density 0.076%

    No Known Activations