© 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. 10-RES-JB
    11. 13745
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploring and traveling

    oai_token-act-pair · gpt-3.5-turbo

    the word "with" and its variations to emphasize relationships or connections

    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
    bilt
    -0.74
     cheaply
    -0.63
    sov
    -0.62
     bip
    -0.59
     shore
    -0.58
    lio
    -0.58
     unlucky
    -0.58
     supra
    -0.58
    uce
    -0.57
    strate
    -0.57
    POSITIVE LOGITS
    draw
    0.96
     regards
    0.82
    drawn
    0.81
    holding
    0.78
     regard
    0.78
     Intent
    0.72
    amaz
    0.71
    ots
    0.70
    ivities
    0.68
    resses
    0.66
    Activations Density 0.052%

    No Known Activations