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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 166
    Prev
    Next
    INDEX
    Explanations

    lines or breaks (such as underscores or ellipses) that suggest a pause or separation in the text

    oai_token-act-pair · gpt-4-turbo

    scenes or breaks in text marked by specific patterns of underscores ('_')

    oai_token-act-pair · gpt-3.5-turbo

    symbols and underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oise
    -0.70
    scl
    -0.70
    outed
    -0.69
    oscope
    -0.66
     Dynamics
    -0.66
    oming
    -0.65
    sis
    -0.65
    aido
    -0.64
    ippi
    -0.63
    ymph
    -0.62
    POSITIVE LOGITS
    SOURCE
    0.89
     ___
    0.85
    kw
    0.77
    !/
    0.71
    KEN
    0.70
    LINE
    0.69
    DIV
    0.69
    quote
    0.69
    ""
    0.68
    ELL
    0.68
    Activations Density 0.012%

    No Known Activations