© 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. 11-RES-JB
    11. 1826
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causality or conditions related to specific quantities or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dig
    -0.78
    ivals
    -0.75
    lest
    -0.75
    enaries
    -0.73
    tops
    -0.71
    fman
    -0.71
    emouth
    -0.69
     cheered
    -0.68
    odied
    -0.67
    vier
    -0.67
    POSITIVE LOGITS
     cumbers
    1.57
     inability
    1.42
     lack
    1.38
     impossibility
    1.32
     inexper
    1.26
     absence
    1.24
     inacc
    1.24
     nature
    1.24
     shortage
    1.22
     scarcity
    1.19
    Activations Density 0.333%

    No Known Activations