© 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. 4-RES-JB
    11. 10461
    Prev
    Next
    INDEX
    Explanations

    phrases related to long-term benefits or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing long-term implications or benefits

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

    No Comments

    Negative Logits
    Rated
    -0.66
    SK
    -0.65
     Mens
    -0.64
    wb
    -0.63
     Cosponsors
    -0.61
    20439
    -0.60
     Alloy
    -0.60
     tur
    -0.58
    olver
    -0.58
    edIn
    -0.57
    POSITIVE LOGITS
    anwhile
    0.76
    grounds
    0.75
     totality
    0.73
    onies
    0.71
    hedon
    0.70
    nings
    0.70
    stakes
    0.70
    ecycle
    0.69
    ways
    0.67
    forts
    0.67
    Activations Density 0.067%

    No Known Activations