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. 4-RES-JB
    6. 3762
    Prev
    Next
    INDEX
    Explanations

    code snippets containing the arrow function syntax '=>' followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax associated with functions and requests

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

    No Comments

    Negative Logits
    iple
    -0.95
    ipel
    -0.85
    alach
    -0.82
    unte
    -0.77
    riet
    -0.76
    hyde
    -0.74
    udes
    -0.74
    resa
    -0.74
    ooks
    -0.73
    ramer
    -0.73
    POSITIVE LOGITS
     {"
    0.84
     ({
    0.76
     nil
    0.75
     {}
    0.71
     undefined
    0.69
     none
    0.69
     Ùħ
    0.69
     infinity
    0.68
     APPLIC
    0.68
     Ø
    0.68
    Activations Density 0.009%

    No Known Activations