© 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. 0-RES-JB
    11. 2813
    Prev
    Next
    INDEX
    Explanations

    anything related to financial profit or gain

    oai_token-act-pair · gpt-3.5-turbo

    references to financial gains or profits

    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
    olk
    -0.64
    alk
    -0.64
    mire
    -0.61
    OH
    -0.60
    usp
    -0.59
    strate
    -0.59
    odi
    -0.59
    UG
    -0.59
     RFC
    -0.59
    sv
    -0.58
    POSITIVE LOGITS
     profits
    3.71
     profit
    2.69
     profitability
    2.16
     Profit
    2.14
     revenues
    1.93
    profits
    1.90
     proceeds
    1.85
     profitable
    1.73
     royalties
    1.71
     earnings
    1.68
    Activations Density 0.008%

    No Known Activations