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. 1-RES-JB
    6. 17233
    Prev
    Next
    INDEX
    Explanations

    programming concepts or terms related to the programming language Lisp

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the programming language Lisp

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Valent
    -0.67
     Greenwich
    -0.67
     Idol
    -0.65
     bear
    -0.63
     rabbits
    -0.63
     Apostles
    -0.62
     consideration
    -0.62
     detail
    -0.60
     Alpine
    -0.60
     fixation
    -0.60
    POSITIVE LOGITS
    isp
    1.27
    ensable
    1.05
    yrus
    0.94
    ionage
    0.93
    olitics
    0.93
    ipeg
    0.92
    yip
    0.90
    olicy
    0.89
    heric
    0.88
    ozy
    0.85
    Activations Density 0.006%

    No Known Activations