© 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. 9-RES-JB
    6. 7137
    Prev
    Next
    INDEX
    Explanations

    HTML or programming related terms within text

    oai_token-act-pair · gpt-3.5-turbo

    programming language keywords and elements related to data structures or software architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.69
    accompan
    -0.65
     INCLUD
    -0.64
     pione
    -0.63
    ¥µ
    -0.61
    ittee
    -0.59
    wcs
    -0.58
    hement
    -0.58
     UNITED
    -0.57
    cipled
    -0.56
    POSITIVE LOGITS
    _
    2.04
    _{
    1.44
    _.
    1.35
    _>
    1.31
    ___
    1.27
    _-
    1.24
    _(
    1.22
     _
    1.17
    __
    1.10
    _-_
    1.08
    Activations Density 0.049%

    No Known Activations