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. 8-RES-JB
    6. 460
    Prev
    Next
    INDEX
    Explanations

    commands and instructions for computer programs and systems

    oai_token-act-pair · gpt-3.5-turbo

    file paths or directory structures in a computing context

    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
     Beir
    -0.86
     Sie
    -0.71
     CPC
    -0.70
     Faul
    -0.70
     Puzz
    -0.68
     Parables
    -0.68
     Schultz
    -0.68
     Faw
    -0.67
     Darius
    -0.66
     Malf
    -0.66
    POSITIVE LOGITS
    tmp
    1.42
    usr
    1.40
    Users
    1.36
    home
    1.26
    Applications
    1.19
    bin
    1.14
    path
    1.13
    api
    1.13
    var
    1.12
    proc
    1.11
    Activations Density 0.058%

    No Known Activations