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. 2-RES-JB
    6. 2264
    Prev
    Next
    INDEX
    Explanations

    references to various organizations or entities that should have been able to help or should have been involved in a situation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and punctuation marks indicating lists or continuations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OME
    -0.64
    iple
    -0.61
    herent
    -0.60
    ety
    -0.57
    ¬¼
    -0.57
    natureconservancy
    -0.56
    resa
    -0.56
    ¦
    -0.56
     redes
    -0.55
     metic
    -0.54
    POSITIVE LOGITS
     albeit
    1.06
     etc
    1.00
     although
    0.92
     namely
    0.91
     respectively
    0.85
     whereas
    0.80
     aka
    0.78
     alas
    0.78
     including
    0.74
     though
    0.74
    Activations Density 1.761%

    No Known Activations