© 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. 1-RES-JB
    11. 2705
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions or moving from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    references to account transfers or transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anita
    -0.72
    Cola
    -0.63
    à©
    -0.63
    GH
    -0.63
    194
    -0.62
     Howe
    -0.62
     Men
    -0.61
    ttp
    -0.61
    enegger
    -0.60
     Stupid
    -0.60
    POSITIVE LOGITS
     transfers
    1.19
     transfer
    1.14
    Transfer
    0.97
     Transfer
    0.93
     transferring
    0.89
    transfer
    0.85
    ster
    0.82
    ability
    0.82
    able
    0.81
     recipients
    0.80
    Activations Density 0.009%

    No Known Activations