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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 0
    Prev
    Next
    INDEX
    Explanations

    mathematical equations involving variables and functions

    oai_token-act-pair · gpt-3.5-turbo

    mathematical functions and their relationships in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indust
    -0.80
     invitations
    -0.72
    naissance
    -0.68
    wcs
    -0.64
    Organ
    -0.64
    20439
    -0.63
     Samantha
    -0.63
    å§
    -0.61
    eer
    -0.60
    techn
    -0.60
    POSITIVE LOGITS
    \)
    0.89
    ^{
    0.89
    â̲
    0.87
    +
    0.83
     =
    0.83
    ||
    0.82
    âĪĴ
    0.81
     ->
    0.78
    =
    0.77
     âĨĴ
    0.77
    Activations Density 0.115%

    No Known Activations