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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22778
    Prev
    Next
    INDEX
    Explanations

    phrases indicating physical movements or actions involving objects

    oai_token-act-pair · gpt-3.5-turbo

    elements related to affection and attachment

    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
     monarchy
    -0.55
     Accountability
    -0.53
    leground
    -0.52
     comprehens
    -0.52
    criminal
    -0.52
    pects
    -0.52
     Ratings
    -0.51
     Teachers
    -0.51
    rosso
    -0.51
     Colleges
    -0.50
    POSITIVE LOGITS
    gently
    0.66
     slur
    0.59
     refill
    0.56
     driveway
    0.54
     prest
    0.53
     photoc
    0.53
     chewing
    0.53
     aeros
    0.53
     mim
    0.53
     convertible
    0.53
    Activations Density 1.912%

    No Known Activations