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. 5503
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements, such as colons and brackets

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and special characters within directives or instructions

    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
     characteristic
    -0.68
     consequential
    -0.67
     Kaz
    -0.66
     Slug
    -0.65
     Tsukuyomi
    -0.63
    YING
    -0.63
     Ninth
    -0.62
    quickShipAvailable
    -0.62
     glasses
    -0.62
     Circus
    -0.61
    POSITIVE LOGITS
    create
    1.42
    activate
    1.23
    make
    1.23
    apply
    1.22
    have
    1.17
    imize
    1.15
    replace
    1.14
    rouse
    1.12
    raise
    1.12
    fill
    1.10
    Activations Density 0.297%

    No Known Activations