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. 11-RES-JB
    6. 22875
    Prev
    Next
    INDEX
    Explanations

    social and cultural references in the text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    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
    NRS
    -0.65
    amaz
    -0.60
    amina
    -0.60
    ulum
    -0.60
    iless
    -0.59
    kj
    -0.59
    ¬¼
    -0.59
    Write
    -0.58
    eem
    -0.58
    isl
    -0.56
    POSITIVE LOGITS
     albeit
    1.11
     although
    1.10
     evidenced
    1.01
     namely
    0.96
     presumably
    0.95
     though
    0.95
    possibly
    0.95
     implying
    0.94
     despite
    0.94
     whilst
    0.92
    Activations Density 0.321%

    No Known Activations