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. 8-RES-JB
    6. 1646
    Prev
    Next
    INDEX
    Explanations

    words related to positive and negative aspects or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to fluctuations or variations in experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saud
    -0.68
     Mecca
    -0.66
    MENTS
    -0.64
     Heist
    -0.63
    Äĩ
    -0.62
     Masters
    -0.60
    EVA
    -0.60
     Sau
    -0.60
     Buddha
    -0.59
    âĢ¢âĢ¢
    -0.58
    POSITIVE LOGITS
    ources
    1.40
    creen
    1.39
    ourced
    1.39
    hirt
    1.36
    ummer
    1.35
    aturated
    1.33
    iders
    1.29
    ocial
    1.27
    ettings
    1.26
    peed
    1.26
    Activations Density 0.112%

    No Known Activations