© 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. 1062
    Prev
    Next
    INDEX
    Explanations

    terms related to high profit or money-making opportunities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial gain or profitability

    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
    amp
    -0.68
    Ì
    -0.67
    ä
    -0.65
     Temperature
    -0.64
    onew
    -0.63
    ansk
    -0.62
     Panel
    -0.61
     Miranda
    -0.59
     cm
    -0.59
    cm
    -0.59
    POSITIVE LOGITS
     lucrative
    3.24
     profitable
    3.12
     profitability
    1.64
     fruitful
    1.61
     costly
    1.59
     advantageous
    1.48
     prosperous
    1.43
     profits
    1.38
     booming
    1.37
     valuable
    1.36
    Activations Density 0.020%

    No Known Activations