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. 2-RES-JB
    6. 18164
    Prev
    Next
    INDEX
    Explanations

    words related to physical locations or directions, particularly those related to the concept of 'side'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "side"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lio
    -0.81
    erick
    -0.81
    ancies
    -0.70
    pload
    -0.69
    iott
    -0.69
    ãģ®å®
    -0.66
    ulet
    -0.66
    erion
    -0.65
    cci
    -0.65
     contagious
    -0.65
    POSITIVE LOGITS
    side
    1.11
    wards
    0.81
    ward
    0.77
    Edge
    0.75
    stones
    0.73
    wise
    0.70
    kick
    0.70
    boarding
    0.69
     Side
    0.67
    medi
    0.65
    Activations Density 0.006%

    No Known Activations