© 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. 1256
    Prev
    Next
    INDEX
    Explanations

    terms related to physics and scientific concepts

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and adjectives indicating manner or relation

    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
     Chiefs
    -0.73
    eland
    -0.72
     Riders
    -0.71
     Payne
    -0.71
     Pirate
    -0.70
     Vikings
    -0.69
     Kodi
    -0.68
    GER
    -0.67
     Meteor
    -0.67
     Jarvis
    -0.66
    POSITIVE LOGITS
     speaking
    0.95
     minded
    0.92
    ãĤ©
    0.89
     inclined
    0.83
     Gleaming
    0.82
     challenged
    0.74
     opposed
    0.74
     Speaking
    0.73
     altering
    0.72
    rics
    0.71
    Activations Density 0.050%

    No Known Activations