© 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. 688
    Prev
    Next
    INDEX
    Explanations

    keywords related to instructions or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'presidency' and its related terms

    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
    finder
    -0.71
    Bear
    -0.71
     Isles
    -0.70
    rosis
    -0.69
    ISM
    -0.67
    Dear
    -0.67
     Paradise
    -0.67
     Rite
    -0.64
    beans
    -0.64
     Sense
    -0.63
    POSITIVE LOGITS
    ervative
    1.02
     pres
    0.97
    ervatives
    0.94
    erver
    0.94
    umes
    0.90
    idium
    0.86
    umer
    0.85
    chool
    0.85
    byter
    0.82
    umed
    0.82
    Activations Density 0.010%

    No Known Activations