© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10668
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to financial transactions or legal procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental or legal 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
     strat
    -0.73
     knot
    -0.73
     Hermes
    -0.70
     Christensen
    -0.70
     wedge
    -0.69
     loaf
    -0.69
     Meteor
    -0.63
     Glover
    -0.62
     Moss
    -0.62
     Frie
    -0.61
    POSITIVE LOGITS
    ufact
    1.20
    asures
    0.90
    atives
    0.90
    onse
    0.90
    llor
    0.90
    utic
    0.89
    owship
    0.87
    isance
    0.86
    irements
    0.85
    gage
    0.83
    Activations Density 0.051%

    No Known Activations