© 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. 7-RES-JB
    11. 2022
    Prev
    Next
    INDEX
    Explanations

    pronouns related to the audience or the speaker

    oai_token-act-pair · gpt-3.5-turbo

    references to the collective "us."

    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
    lets
    -0.64
    fect
    -0.64
    tein
    -0.61
     CPC
    -0.58
    ussen
    -0.57
     livest
    -0.57
    Offic
    -0.56
     MAC
    -0.55
    stick
    -0.55
     chaired
    -0.55
    POSITIVE LOGITS
    selves
    1.20
    hers
    1.16
    ern
    0.91
    urers
    0.89
    aning
    0.89
     ourselves
    0.88
     selves
    0.85
    ury
    0.79
    urious
    0.79
    leep
    0.78
    Activations Density 0.062%

    No Known Activations