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. 1-RES-JB
    6. 24353
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "handedness", specifically the term "handed" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to handedness, particularly in relation to left-handedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouf
    -0.73
    lé
    -0.70
    LAN
    -0.68
     Delta
    -0.68
    CHAT
    -0.68
     Detect
    -0.68
     Scores
    -0.66
     Eps
    -0.66
    Tonight
    -0.66
    ETF
    -0.66
    POSITIVE LOGITS
    handed
    1.31
     nodd
    1.07
    maid
    0.92
     showc
    0.88
    footed
    0.85
    hander
    0.82
     destro
    0.82
     enthusi
    0.79
     axe
    0.78
    ragon
    0.77
    Activations Density 0.007%

    No Known Activations