© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19024
    Prev
    Next
    INDEX
    Explanations

    slight differences or variations in attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to minimal or minor changes and effects

    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
    hell
    -0.74
    hel
    -0.69
     Communities
    -0.66
    umen
    -0.65
    aire
    -0.65
    ios
    -0.65
    ets
    -0.64
     Sciences
    -0.63
    naires
    -0.62
    az
    -0.62
    POSITIVE LOGITS
     slight
    3.26
     faint
    1.67
     slightest
    1.56
     slightly
    1.49
     minor
    1.47
     subtle
    1.32
     mild
    1.31
     negligible
    1.19
     noticeable
    1.19
     gradual
    1.14
    Activations Density 0.014%

    No Known Activations