© 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. 11-RES-JB
    11. 17467
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions or terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial transactions and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Historically
    -0.61
     venerable
    -0.59
     Filipino
    -0.59
     Ori
    -0.58
     Traditional
    -0.58
     Administrator
    -0.58
     Native
    -0.58
     Religious
    -0.56
    particularly
    -0.56
     Sikh
    -0.56
    POSITIVE LOGITS
     thresholds
    0.93
     tokens
    0.92
    votes
    0.91
     clauses
    0.87
     bets
    0.85
     ballots
    0.85
     tags
    0.85
    cards
    0.83
     markers
    0.82
     shots
    0.82
    Activations Density 0.920%

    No Known Activations