© 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. 2-RES-JB
    11. 12609
    Prev
    Next
    INDEX
    Explanations

    calculations or numerical estimates in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to mathematical calculations or estimations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oho
    -0.80
    Bio
    -0.71
    por
    -0.69
     Bengal
    -0.66
     Plains
    -0.65
    gage
    -0.63
    ifest
    -0.63
     Ment
    -0.62
    Guest
    -0.62
    anch
    -0.61
    POSITIVE LOGITS
     calculations
    1.21
     calculation
    1.15
     equations
    1.04
     computation
    0.91
     calculating
    0.88
    ithmetic
    0.85
     calculates
    0.83
     comput
    0.82
     arithmetic
    0.82
     Calcul
    0.80
    Activations Density 0.020%

    No Known Activations