Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 17503
    Prev
    Next
    INDEX
    Explanations

    phrases related to sowing seeds or planting

    oai_token-act-pair · gpt-3.5-turbo

    words related to obligations or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caldwell
    -0.73
     pinch
    -0.62
    cube
    -0.61
     infiltrate
    -0.60
     forge
    -0.59
    agi
    -0.56
     Solitaire
    -0.55
     Crime
    -0.55
     Exile
    -0.54
     Cole
    -0.54
    POSITIVE LOGITS
    owed
    1.20
    ows
    1.04
    owing
    0.99
    ielding
    0.88
    ower
    0.85
    idth
    0.83
    NESS
    0.82
    OWS
    0.81
    own
    0.80
    tons
    0.77
    Activations Density 0.006%

    No Known Activations