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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 15688
    Prev
    Next
    INDEX
    Explanations

    phrases related to change or decline

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hold
    -0.68
    theless
    -0.67
    sama
    -0.67
    umbledore
    -0.63
    lace
    -0.62
    creen
    -0.60
    weather
    -0.60
    uctor
    -0.59
    sche
    -0.59
     Bever
    -0.59
    POSITIVE LOGITS
     extinct
    1.12
     overboard
    1.06
     bankrupt
    1.02
     unnoticed
    0.93
     nowhere
    0.90
     crazy
    0.90
    vt
    0.89
     insane
    0.89
     nuts
    0.87
     rogue
    0.87
    Activations Density 0.077%

    No Known Activations