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. 0-RES-JB
    6. 16050
    Prev
    Next
    INDEX
    Explanations

    statistics related to various topics like public opinion, medical procedures, and scientific beliefs

    oai_token-act-pair · gpt-3.5-turbo

    percentage figures in data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     rein
    -0.57
     elephant
    -0.56
     early
    -0.55
     Marshal
    -0.54
     Cy
    -0.54
     instant
    -0.54
     Ram
    -0.53
     spur
    -0.53
     Soy
    -0.53
     San
    -0.53
    POSITIVE LOGITS
    %)
    3.64
    %).
    2.45
    %),
    2.38
    %]
    2.10
    %);
    2.08
    %"
    2.04
    +)
    2.01
    /)
    1.97
    *)
    1.81
    %-
    1.77
    Activations Density 0.010%

    No Known Activations