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. 7-RES-JB
    6. 10771
    Prev
    Next
    INDEX
    Explanations

    words related to meanings or translations into different languages

    oai_token-act-pair · gpt-3.5-turbo

    definitions or meanings attributed to names or terms

    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
    iments
    -0.73
    olicy
    -0.73
    icides
    -0.69
     clicks
    -0.65
    ucket
    -0.64
    metry
    -0.64
    ettings
    -0.64
    iment
    -0.64
    icidal
    -0.64
    erest
    -0.64
    POSITIVE LOGITS
    literally
    1.05
    meaning
    0.99
     Dwell
    0.88
     plural
    0.85
    God
    0.84
     pronounced
    0.83
    å¯
    0.78
    ç¥ŀ
    0.76
     Literally
    0.76
    Spanish
    0.76
    Activations Density 0.163%

    No Known Activations