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. 9-RES-JB
    6. 6406
    Prev
    Next
    INDEX
    Explanations

    words that are homophones or closely related to "so"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     innocence
    -0.65
    theless
    -0.62
     misconception
    -0.62
     envy
    -0.60
     royalty
    -0.59
    DERR
    -0.59
     resemblance
    -0.58
     aristocracy
    -0.57
     FAA
    -0.57
     appeal
    -0.57
    POSITIVE LOGITS
    ppy
    1.19
    bered
    1.15
    vere
    1.14
    oths
    1.13
    pp
    1.09
    fter
    1.09
    pping
    1.09
    FTWARE
    1.09
    aring
    1.08
    aked
    1.07
    Activations Density 0.042%

    No Known Activations