© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 4227
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an overall summary or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in all" and its variations, indicating a focus on inclusivity or totality

    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
    fell
    -0.70
    arthed
    -0.67
    eday
    -0.67
    stadt
    -0.63
     Citation
    -0.63
    bryce
    -0.62
    gaard
    -0.62
    raction
    -0.61
    sworth
    -0.61
    ALSE
    -0.59
    POSITIVE LOGITS
    clusive
    1.11
    CLUS
    0.69
     sudden
    0.67
    oots
    0.67
     together
    0.65
     toget
    0.64
    ighter
    0.63
    together
    0.63
    patient
    0.61
    ooting
    0.61
    Activations Density 0.060%

    No Known Activations