© 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. 22993
    Prev
    Next
    INDEX
    Explanations

    words related to chemical elements and compounds

    oai_token-act-pair · gpt-3.5-turbo

    technical or scientific terminology

    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
     PB
    -0.76
     Guid
    -0.76
     Hon
    -0.76
     Mt
    -0.74
     Jiu
    -0.73
     SAN
    -0.71
     Towns
    -0.71
     TW
    -0.70
     Hack
    -0.69
     Coff
    -0.69
    POSITIVE LOGITS
    ldom
    1.05
    odes
    0.97
    ouse
    0.94
    asses
    0.94
    acular
    0.93
    role
    0.93
    opter
    0.93
    iasis
    0.92
    uries
    0.92
    rium
    0.92
    Activations Density 0.127%

    No Known Activations