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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23915
    Prev
    Next
    INDEX
    Explanations

    words related to body parts and their condition, focusing on eyes and mouth in particular

    oai_token-act-pair · gpt-3.5-turbo

    anatomical features and body parts related to health and surgery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CAST
    -0.79
    igslist
    -0.71
    advertising
    -0.67
    Crime
    -0.66
    DEM
    -0.66
    Sund
    -0.65
     Flavoring
    -0.65
    ombie
    -0.65
     guiActiveUn
    -0.64
    ionage
    -0.63
    POSITIVE LOGITS
     cavity
    1.00
     circumference
    0.99
     lobe
    0.85
     canal
    0.82
     hump
    0.82
     anatomy
    0.82
     diameter
    0.81
    pan
    0.80
    stem
    0.78
     curv
    0.78
    Activations Density 0.118%

    No Known Activations