Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4711
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to subscriptions or services

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "SU" associated with various contexts

    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
     Lap
    -0.81
    lique
    -0.77
    bench
    -0.77
    ipple
    -0.75
    antle
    -0.73
    ocket
    -0.72
    ald
    -0.71
    mill
    -0.69
    mith
    -0.66
     Barth
    -0.65
    POSITIVE LOGITS
     SU
    3.99
    SU
    1.76
     SUB
    1.34
     Su
    1.30
    Su
    1.22
    su
    1.17
     SUV
    1.07
     SIGN
    1.05
     su
    1.03
     TRANS
    1.01
    Activations Density 0.010%

    No Known Activations