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. 0-RES-JB
    6. 8444
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical precision and measurements

    oai_token-act-pair · gpt-3.5-turbo

    mentions or references to fractions or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Buk
    -0.59
     compatible
    -0.59
     Pavilion
    -0.57
     Boyd
    -0.56
     Rocket
    -0.56
     Pull
    -0.56
     Robinson
    -0.56
     provoked
    -0.54
    illary
    -0.54
     paved
    -0.53
    POSITIVE LOGITS
    ths
    5.16
    th
    1.47
    thens
    1.35
    thening
    1.31
    TH
    1.28
    thing
    1.21
    teenth
    1.20
    thy
    1.17
    tha
    1.11
    tons
    1.11
    Activations Density 0.010%

    No Known Activations