© 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. 3-RES-JB
    11. 1811
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters or official reports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to deportation or related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipedia
    -0.62
    KNOWN
    -0.62
    ingen
    -0.61
    vana
    -0.60
     dodge
    -0.59
    wana
    -0.59
    wat
    -0.59
    enium
    -0.59
    antha
    -0.59
    fair
    -0.59
    POSITIVE LOGITS
    achment
    0.92
    ngth
    0.88
    ement
    0.75
    ment
    0.69
     Lauder
    0.69
    ordinary
    0.67
    ennes
    0.64
    PsyNetMessage
    0.64
    ctions
    0.63
    cuts
    0.63
    Activations Density 0.060%

    No Known Activations