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. 7-RES-JB
    6. 13113
    Prev
    Next
    INDEX
    Explanations

    statements related to legal actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    assertive expressions of opinion or position statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OG
    -0.85
     crap
    -0.74
     Haku
    -0.69
    stuff
    -0.68
     Gum
    -0.68
     Semi
    -0.67
     Grav
    -0.66
    cum
    -0.66
    Posts
    -0.66
     Tie
    -0.65
    POSITIVE LOGITS
     intend
    1.06
    've
    1.06
     congratulate
    1.04
     conclude
    1.02
     respectfully
    1.02
     believe
    0.99
     hereby
    0.98
     sincerely
    0.98
     presume
    0.96
     applaud
    0.96
    Activations Density 0.351%

    No Known Activations