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. 8-RES-JB
    6. 20521
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions and movements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant societal or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.67
    venants
    -0.66
    Ô
    -0.63
    worldly
    -0.63
    speak
    -0.60
    atile
    -0.59
    avez
    -0.59
    District
    -0.58
    binary
    -0.58
     presence
    -0.58
    POSITIVE LOGITS
     necks
    0.82
     shoulders
    0.66
     jerk
    0.66
     neck
    0.65
     Hog
    0.62
     Hop
    0.62
     Fever
    0.60
    oche
    0.60
    steen
    0.60
     Neck
    0.60
    Activations Density 0.170%

    No Known Activations