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. 10-RES-JB
    6. 22893
    Prev
    Next
    INDEX
    Explanations

    actions that people must take or things they need to do

    oai_token-act-pair · gpt-3.5-turbo

    imperative statements related to necessary actions or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.83
     Milky
    -0.69
     Voy
    -0.66
     unlucky
    -0.66
     Mayhem
    -0.66
    ELD
    -0.66
    Mech
    -0.64
    Runner
    -0.61
     amusement
    -0.61
     Coff
    -0.61
    POSITIVE LOGITS
     rethink
    1.38
     prioritize
    1.34
     empower
    1.30
     ensure
    1.25
     broaden
    1.25
     educate
    1.25
     strive
    1.23
     recognize
    1.23
     intensify
    1.22
     embrace
    1.19
    Activations Density 0.175%

    No Known Activations