Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 6993
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical actions involving body parts

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving physical actions related to rolling or upward movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auna
    -0.86
    etsk
    -0.83
    orage
    -0.81
    eele
    -0.76
    uo
    -0.71
    cius
    -0.70
    orea
    -0.69
    iae
    -0.69
    aline
    -0.69
    affer
    -0.68
    POSITIVE LOGITS
     sleeves
    0.97
     curtains
    0.80
     punches
    0.74
     shoulders
    0.71
     mirrors
    0.71
     shotgun
    0.70
     dice
    0.70
     canopy
    0.70
     suitcase
    0.70
     stacked
    0.68
    Activations Density 0.082%

    No Known Activations