© 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. 0-RES-JB
    11. 5360
    Prev
    Next
    INDEX
    Explanations

    mentions of financial matters and responsibilities, particularly related to fraud or stability

    oai_token-act-pair · gpt-3.5-turbo

    topics related to financial accountability and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interchange
    -0.69
    oqu
    -0.69
     threaded
    -0.66
     Sequence
    -0.64
     Mata
    -0.63
    Origin
    -0.63
    inct
    -0.63
    uo
    -0.62
     Moments
    -0.62
     variation
    -0.62
    POSITIVE LOGITS
     financially
    3.35
     finances
    2.15
    financial
    1.69
     financial
    1.63
    Financial
    1.57
     economically
    1.40
     bankrupt
    1.35
    funding
    1.35
     profitability
    1.32
     financed
    1.30
    Activations Density 0.021%

    No Known Activations