© 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. 9-RES-JB
    11. 7257
    Prev
    Next
    INDEX
    Explanations

    words related to the activity of hopping

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hop" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anguage
    -0.70
    $$$$
    -0.67
    ateral
    -0.67
     conclud
    -0.65
    UD
    -0.64
     Dynamics
    -0.63
     reconc
    -0.59
    ude
    -0.59
    UCT
    -0.59
     McGu
    -0.58
    POSITIVE LOGITS
    eful
    1.30
    efully
    1.26
    eless
    1.18
    Hop
    1.12
    emaker
    1.01
    lite
    0.99
    fen
    0.87
    hop
    0.83
    retty
    0.81
    olic
    0.80
    Activations Density 0.031%

    No Known Activations