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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3876
    Prev
    Next
    INDEX
    Explanations

    occurrences of pencils in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to writing instruments, particularly pencils and chalk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worthiness
    -0.72
    nat
    -0.72
    Imm
    -0.71
    iety
    -0.71
    Fed
    -0.70
    Domain
    -0.70
    tra
    -0.69
     Internal
    -0.68
    vm
    -0.66
    forces
    -0.65
    POSITIVE LOGITS
     pencil
    4.00
     pen
    1.51
     chalk
    1.40
     pens
    1.38
     ink
    1.35
     scissors
    1.27
     scrib
    1.26
     typew
    1.25
     handwriting
    1.14
     notebooks
    1.13
    Activations Density 0.023%

    No Known Activations