© 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. 10-RES-JB
    11. 11123
    Prev
    Next
    INDEX
    Explanations

    financial figures and units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.66
    Synopsis
    -0.66
    ady
    -0.65
    ctor
    -0.65
    activ
    -0.64
    iddler
    -0.62
    bris
    -0.61
    Led
    -0.61
    gorithm
    -0.61
    beat
    -0.59
    POSITIVE LOGITS
     apiece
    1.11
     increments
    1.10
    +.
    1.03
     total
    0.97
     altogether
    0.91
     difference
    0.85
     TOTAL
    0.82
     respectively
    0.82
    -$
    0.80
     per
    0.80
    Activations Density 0.280%

    No Known Activations