© 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. 0-RES-JB
    11. 20763
    Prev
    Next
    INDEX
    Explanations

    variations or changes in values within a set of data

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to variation or changes in conditions

    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
     Rab
    -0.63
     Ever
    -0.62
    aband
    -0.61
     Signs
    -0.58
     Es
    -0.57
     Mark
    -0.57
     EVER
    -0.56
     fears
    -0.56
     Had
    -0.55
     Team
    -0.55
    POSITIVE LOGITS
     vary
    3.45
     varies
    2.63
     differ
    2.35
     varied
    1.99
     differed
    1.77
     differs
    1.66
     varying
    1.56
     fluct
    1.40
     variation
    1.37
     depends
    1.33
    Activations Density 0.021%

    No Known Activations