© 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. 4-RES-JB
    11. 10511
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movement or action of jumping or leaping

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to jumping or transitioning

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

    No Comments

    Negative Logits
    Policy
    -0.78
    heastern
    -0.70
    ãĥĩãĤ£
    -0.63
     Bild
    -0.63
    marks
    -0.62
    Limited
    -0.62
    Weak
    -0.61
    foreign
    -0.59
     Peoples
    -0.59
    weak
    -0.59
    POSITIVE LOGITS
     sidx
    1.00
     heights
    0.84
    obin
    0.83
     hoops
    0.80
     heels
    0.77
     stairs
    0.76
    adders
    0.72
     leaps
    0.72
     torches
    0.71
    ioxide
    0.71
    Activations Density 0.155%

    No Known Activations