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. 10-RES-JB
    6. 9843
    Prev
    Next
    INDEX
    Explanations

    technical and industrial terms, particularly related to hardware components and manufacturing materials

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various types of objects and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.85
    iversary
    -0.61
    Lear
    -0.59
    REDACTED
    -0.58
    ãĥĥãĥī
    -0.57
     gratitude
    -0.55
    ãĥ©ãĥ³
    -0.55
    staking
    -0.55
     captcha
    -0.55
    ãĥ¡
    -0.55
    POSITIVE LOGITS
     (>
    1.25
     (<
    1.23
     such
    1.16
    hips
    1.05
     like
    1.00
    paces
    0.97
    such
    0.96
     alike
    0.94
     (.
    0.88
     whose
    0.86
    Activations Density 0.578%

    No Known Activations