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. 4787
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    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
     withd
    -0.98
     manif
    -0.80
     inver
    -0.79
     cabbage
    -0.75
     brut
    -0.74
     prototyp
    -0.74
     scaling
    -0.73
    onga
    -0.70
     challeng
    -0.70
     listeners
    -0.70
    POSITIVE LOGITS
     Retrieved
    1.55
    jpg
    1.46
     Accessed
    1.32
    png
    1.25
    htm
    1.17
    txt
    1.12
    pdf
    1.11
    zip
    1.10
    exe
    1.10
    wav
    1.08
    Activations Density 0.298%

    No Known Activations