Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22352
    Prev
    Next
    INDEX
    Explanations

    instances of the word "So"

    oai_token-act-pair · gpt-3.5-turbo

    the word "so" in various contexts

    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
     innocence
    -0.65
    lain
    -0.60
     virginity
    -0.59
    wreck
    -0.58
     royalty
    -0.58
     sequ
    -0.55
     upside
    -0.55
     appeal
    -0.55
     resemblance
    -0.55
     juggling
    -0.55
    POSITIVE LOGITS
    bered
    1.21
    apy
    1.18
    aring
    1.15
    fter
    1.15
    FTWARE
    1.14
    vere
    1.13
    oths
    1.12
    aked
    1.11
    ppy
    1.06
    othe
    1.06
    Activations Density 0.033%

    No Known Activations