© 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. 7-RES-JB
    11. 23979
    Prev
    Next
    INDEX
    Explanations

    phrases related to hands-on activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating hands-on experiences

    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
     Pell
    -0.64
     Jacket
    -0.62
     Coat
    -0.62
     Cruiser
    -0.61
     Shepherd
    -0.60
     circumstance
    -0.60
     Carth
    -0.58
     disturbance
    -0.58
     Ascension
    -0.58
     Shelter
    -0.58
    POSITIVE LOGITS
    everal
    1.36
    sembly
    1.24
    ettings
    1.13
    hell
    1.06
    peed
    1.04
    hift
    0.99
    ource
    0.99
    Downloadha
    0.98
    hire
    0.98
    hot
    0.97
    Activations Density 0.066%

    No Known Activations