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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 20554
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to functionality or helpfulness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of usefulness or practicality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ran
    -0.76
     Anthem
    -0.76
    istan
    -0.70
    rix
    -0.70
     Pledge
    -0.62
     backdrop
    -0.61
    had
    -0.59
     accuser
    -0.59
     Ocean
    -0.58
     Television
    -0.58
    POSITIVE LOGITS
     useful
    3.35
     helpful
    2.28
     Useful
    2.22
     valuable
    2.08
     usable
    1.96
     handy
    1.91
     usefulness
    1.88
     invaluable
    1.80
     worthwhile
    1.78
     useless
    1.67
    Activations Density 0.014%

    No Known Activations