© 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. 4-RES-JB
    11. 10281
    Prev
    Next
    INDEX
    Explanations

    numerical calculations or terms related to data analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to mathematical calculations and assessments

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

    No Comments

    Negative Logits
    bley
    -0.82
    Bio
    -0.75
     Ment
    -0.66
    gage
    -0.66
    unal
    -0.65
    isco
    -0.64
     Indies
    -0.63
    VP
    -0.63
    food
    -0.62
    por
    -0.62
    POSITIVE LOGITS
     calculation
    1.10
     calculations
    1.07
     equations
    0.99
     calculating
    0.95
     calculate
    0.92
     Calcul
    0.83
     calculated
    0.79
     calculates
    0.77
    entric
    0.75
    cal
    0.75
    Activations Density 0.024%

    No Known Activations