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. 4-RES-JB
    6. 21259
    Prev
    Next
    INDEX
    Explanations

    Wikipedia citations with specific formatting, most likely related to the presence of 'WH'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "WH," which appears to signify a focus on questioning or inquiry

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

    No Comments

    Negative Logits
    Reloaded
    -0.71
     Grande
    -0.68
    uated
    -0.65
    spection
    -0.63
    bart
    -0.63
     Barton
    -0.61
    feld
    -0.61
    uating
    -0.61
     Gallery
    -0.61
     revolving
    -0.60
    POSITIVE LOGITS
    olly
    1.11
    ilst
    1.10
    soever
    1.06
    istle
    0.98
    itness
    0.98
    ispers
    0.96
    ipl
    0.92
    ILE
    0.92
    oles
    0.90
    ole
    0.89
    Activations Density 0.007%

    No Known Activations