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. 9-RES-JB
    6. 8143
    Prev
    Next
    INDEX
    Explanations

    mentions of specific substances or materials

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.66
     Period
    -0.63
    ãĥ´
    -0.63
    GoldMagikarp
    -0.61
    ãĤ¹ãĥĪ
    -0.59
     Hundreds
    -0.58
    ÃĽ
    -0.58
    HAEL
    -0.58
     Janeiro
    -0.57
     DevOnline
    -0.56
    POSITIVE LOGITS
     looming
    1.03
     etc
    1.01
     lurking
    0.99
     popping
    0.96
     handy
    0.95
     looms
    0.89
     sprinkled
    0.89
     rounding
    0.88
     leftover
    0.86
     shenanigans
    0.83
    Activations Density 0.780%

    No Known Activations