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. 11-RES-JB
    6. 17762
    Prev
    Next
    INDEX
    Explanations

    technical details and features in descriptions of physical objects or locations

    oai_token-act-pair · gpt-3.5-turbo

    specific technical terms and units related to electronic devices and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anyway
    -0.66
     Saying
    -0.63
    ¿
    -0.62
    \":
    -0.60
     anyways
    -0.60
    maxwell
    -0.59
    %);
    -0.58
     Response
    -0.57
     Silence
    -0.57
     Consider
    -0.57
    POSITIVE LOGITS
     debuted
    1.02
     awaits
    1.02
     accompanies
    0.97
     sits
    0.95
     arrived
    0.93
     appeared
    0.92
     emerges
    0.92
     weighs
    0.91
     emerged
    0.90
     surfaced
    0.90
    Activations Density 0.296%

    No Known Activations