© 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. 458
    Prev
    Next
    INDEX
    Explanations

    words related to electronic devices or technology

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to leadership and authority

    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
    SHIP
    -0.73
     goats
    -0.68
     faked
    -0.63
     CPC
    -0.62
    cius
    -0.61
     STATS
    -0.60
    OPLE
    -0.59
    BIP
    -0.56
    obos
    -0.55
    Detailed
    -0.55
    POSITIVE LOGITS
    uchi
    0.80
    Wan
    0.79
    ratulations
    0.76
    hell
    0.73
     Auditor
    0.68
    leck
    0.66
    quit
    0.64
    uct
    0.63
    gress
    0.63
    Connor
    0.62
    Activations Density 0.195%

    No Known Activations