© 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. 2-RES-JB
    6. 9085
    Prev
    Next
    INDEX
    Explanations

    specific programming language syntax related to "::" and "::9"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the '::' syntax used in programming or markup languages

    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
    ividual
    -0.83
    issance
    -0.81
    quished
    -0.79
    lies
    -0.77
    ommel
    -0.77
    unci
    -0.74
    iage
    -0.73
    istle
    -0.72
    olin
    -0.69
    yrus
    -0.69
    POSITIVE LOGITS
    NL
    1.02
    wcsstore
    1.00
    Simple
    0.94
    operator
    0.86
    Parameters
    0.85
    temp
    0.83
    ::
    0.81
    (_
    0.81
    NOT
    0.81
    Runtime
    0.80
    Activations Density 0.008%

    No Known Activations