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. 8804
    Prev
    Next
    INDEX
    Explanations

    names containing the sequence "ih" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ih" 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
     pop
    -0.71
     pie
    -0.69
     aster
    -0.67
     fixture
    -0.64
     snap
    -0.64
     Pop
    -0.64
     popup
    -0.62
     Pie
    -0.61
     dotted
    -0.59
     plaster
    -0.59
    POSITIVE LOGITS
    ih
    4.16
    iy
    1.52
    ij
    1.40
    uh
    1.27
    iw
    1.25
    oh
    1.21
    iq
    1.20
    ika
    1.19
    ich
    1.14
    ihu
    1.13
    Activations Density 0.013%

    No Known Activations