Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 3672
    Prev
    Next
    INDEX
    Explanations

    phrases related to GNU, Linux distributions, and software development tools

    oai_token-act-pair · gpt-3.5-turbo

    mentions of open-source software projects and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idas
    -1.01
    haar
    -0.89
    het
    -0.84
    lete
    -0.82
    lain
    -0.79
    let
    -0.79
    anan
    -0.77
    ilar
    -0.77
    oys
    -0.76
    WHERE
    -0.75
    POSITIVE LOGITS
     GNU
    0.88
     Emacs
    0.85
     FTP
    0.85
     grep
    0.82
    DragonMagazine
    0.81
    BSD
    0.79
     filesystem
    0.78
     Linux
    0.78
     Perl
    0.75
     KDE
    0.74
    Activations Density 0.053%

    No Known Activations