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. 1367
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving specific variables

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and functions

    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
    zona
    -0.70
     Niet
    -0.66
    indust
    -0.65
     invitations
    -0.65
     acron
    -0.64
    naissance
    -0.64
    Organ
    -0.64
     TOUR
    -0.61
     Crowd
    -0.61
    introdu
    -0.60
    POSITIVE LOGITS
    ^{
    1.03
    +
    0.87
    ^
    0.84
     =
    0.83
    _{
    0.83
    \)
    0.80
    ++
    0.80
     âĨĴ
    0.80
     =>
    0.80
    =
    0.79
    Activations Density 0.073%

    No Known Activations