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. 5842
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices, specifically smartphones

    oai_token-act-pair · gpt-3.5-turbo

    references to smartphones and their features

    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
    atorium
    -0.85
     annexation
    -0.65
    rawdownloadcloneembedreportprint
    -0.64
    rius
    -0.62
    stone
    -0.60
     bluff
    -0.60
    REDACTED
    -0.59
     Croat
    -0.58
    Commission
    -0.58
     Lancaster
    -0.57
    POSITIVE LOGITS
    chool
    1.25
    paces
    1.22
    cale
    1.22
    aurus
    1.22
    hips
    1.22
    mith
    1.19
    hip
    1.16
    hare
    1.12
    etting
    1.09
    pring
    1.08
    Activations Density 0.118%

    No Known Activations