© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16452
    Prev
    Next
    INDEX
    Explanations

    words related to the anatomical term "artery."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     convert
    -0.70
     Ali
    -0.63
     shares
    -0.63
     amusement
    -0.62
     SAL
    -0.62
     Equal
    -0.61
     Alibaba
    -0.60
     asset
    -0.60
     construct
    -0.59
     sr
    -0.57
    POSITIVE LOGITS
    neck
    4.70
     necks
    1.51
     Neck
    1.46
    leneck
    1.34
     neck
    1.27
    bottom
    1.11
    thro
    1.07
    bone
    1.06
    nec
    1.05
    bones
    1.05
    Activations Density 0.023%

    No Known Activations