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. 19734
    Prev
    Next
    INDEX
    Explanations

    instances of requirements or conditions for performing certain actions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "have" in various contexts, indicating necessity or obligation

    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
    eem
    -0.60
    review
    -0.58
    Interested
    -0.57
    PC
    -0.54
     Review
    -0.53
    TG
    -0.52
    âĺħ
    -0.52
    cade
    -0.52
    eq
    -0.52
    aucas
    -0.51
    POSITIVE LOGITS
     to
    1.12
     recourse
    1.03
     gotta
    0.93
     difficulty
    0.92
    to
    0.91
     TO
    0.82
     been
    0.82
     trouble
    0.80
     gone
    0.79
     nowhere
    0.77
    Activations Density 0.263%

    No Known Activations