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. 6-RES-JB
    6. 21104
    Prev
    Next
    INDEX
    Explanations

    text related to coding, such as code syntax and programming language elements

    oai_token-act-pair · gpt-3.5-turbo

    technical elements or attributes related to programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -0.86
    ecause
    -0.70
     Canaver
    -0.64
     detrim
    -0.64
    armac
    -0.62
     Rated
    -0.61
    agall
    -0.60
    uden
    -0.59
    ugi
    -0.59
    bringer
    -0.58
    POSITIVE LOGITS
    _
    1.05
     =
    1.01
     :=
    0.95
    ="
    0.93
    Flags
    0.92
     <-
    0.91
    =[
    0.90
    =
    0.90
    =$
    0.81
    ='
    0.78
    Activations Density 0.148%

    No Known Activations