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. 16021
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and locations

    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
    •GPT2 Layer 8 Movie Sentiment Features

    No Comments

    Negative Logits
    Sov
    -0.21
    sic
    -0.20
    tein
    -0.20
    eus
    -0.19
     ben
    -0.18
     destro
    -0.17
    Ń·
    -0.17
    enegger
    -0.17
     Aires
    -0.16
     sul
    -0.16
    POSITIVE LOGITS
     âĢº
    0.17
    atform
    0.16
    Screenshot
    0.16
    onica
    0.15
     isEnabled
    0.15
    Buyable
    0.15
    UGC
    0.15
    okia
    0.15
    reenshots
    0.15
    utterstock
    0.15
    Activations Density 7.910%

    No Known Activations