© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3312
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to processing data and variables in a programming environment, specifically focusing on methods that involve replacing or manipulating text within strings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    code elements and structures in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quo
    -0.72
     rocking
    -0.71
     hindered
    -0.70
     aided
    -0.69
    .—
    -0.68
     pir
    -0.66
     persecuted
    -0.64
     "âĢ¦
    -0.64
     doubted
    -0.63
     elusive
    -0.63
    POSITIVE LOGITS
    append
    1.29
    push
    1.22
    prototype
    1.20
    create
    1.15
    split
    1.14
    inner
    1.14
    clone
    1.13
    each
    1.11
    remove
    1.09
    apply
    1.09
    Activations Density 0.034%

    No Known Activations