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. 0-RES-JB
    6. 9371
    Prev
    Next
    INDEX
    Explanations

    contractions in sentences

    oai_token-act-pair · gpt-3.5-turbo

    contractions of "will" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contrary
    -0.60
     such
    -0.56
    mund
    -0.55
     reporting
    -0.54
     metric
    -0.54
     complex
    -0.52
     identification
    -0.52
     operating
    -0.52
     expressing
    -0.51
     distinguishing
    -0.51
    POSITIVE LOGITS
    'll
    3.07
    'd
    1.83
    've
    1.59
    're
    1.58
     will
    1.50
    'm
    1.40
    will
    1.39
     WILL
    1.39
     shalt
    1.28
    Will
    1.26
    Activations Density 0.019%

    No Known Activations