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. 15586
    Prev
    Next
    INDEX
    Explanations

    personal pronouns "You" or "You've" in the middle of a sentence

    oai_token-act-pair · gpt-3.5-turbo
    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
     srfAttach
    -0.70
    wrapper
    -0.67
    ¿½
    -0.64
     totality
    -0.62
     stemming
    -0.61
     cardinal
    -0.60
    dq
    -0.60
     fundamentals
    -0.59
    ãĥ³ãĤ¸
    -0.59
     cent
    -0.59
    POSITIVE LOGITS
    're
    1.17
    've
    1.14
    'll
    1.09
    Gov
    1.09
     guessed
    1.07
    tu
    1.05
     Tube
    0.97
    ths
    0.95
     Might
    0.93
     know
    0.93
    Activations Density 0.072%

    No Known Activations