© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18981
    Prev
    Next
    INDEX
    Explanations

    keywords related to the concept of "hop", such as "hoping", "Hops Growers", and "Hopkins"

    oai_token-act-pair · gpt-3.5-turbo

    references to hops, commonly associated with brewing or gardening

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $$$$
    -0.70
    anguage
    -0.60
    UCT
    -0.60
     Schwarzenegger
    -0.58
     Dynamics
    -0.57
     Monstrous
    -0.56
     Monarch
    -0.56
     Lloyd
    -0.56
     Frankenstein
    -0.56
     swear
    -0.55
    POSITIVE LOGITS
    efully
    1.64
    eful
    1.64
    eless
    1.27
    emaker
    1.15
    lite
    1.15
    Hop
    1.08
    fen
    0.98
    ef
    0.96
    sticks
    0.93
    along
    0.93
    Activations Density 0.028%

    No Known Activations