© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 17075
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols that are being used in text formatting, programming, or mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols used in coding or programming contexts

    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
     dece
    -0.78
     coup
    -0.71
     synd
    -0.65
     bells
    -0.64
     Hung
    -0.63
     Quadro
    -0.62
     Ferr
    -0.62
     headed
    -0.62
     Feder
    -0.62
     Argentine
    -0.62
    POSITIVE LOGITS
    #$
    1.28
    insert
    1.17
    DATA
    1.11
    future
    1.10
    someone
    1.05
    $
    1.03
    EMA
    1.02
    blank
    1.00
    REDACTED
    1.00
    something
    0.99
    Activations Density 0.167%

    No Known Activations