© 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. 23467
    Prev
    Next
    INDEX
    Explanations

    adjectives describing emotions or assessments

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that describe things as unusual or lacking credibility

    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
    tein
    -0.71
    insula
    -0.69
    agogue
    -0.65
    igion
    -0.63
    angler
    -0.62
    unker
    -0.62
    iculty
    -0.61
    uana
    -0.60
     Appears
    -0.60
    ogie
    -0.60
    POSITIVE LOGITS
    soDeliveryDate
    0.72
     enough
    0.72
    istically
    0.72
     Izan
    0.71
    ISH
    0.71
    ãģĨ
    0.70
    ALLY
    0.69
    vier
    0.68
     lately
    0.64
    ish
    0.63
    Activations Density 0.154%

    No Known Activations