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. 16735
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "so"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "so-called" 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
    theless
    -0.69
     NTS
    -0.65
     Mens
    -0.58
     takedown
    -0.56
     upside
    -0.56
     MFT
    -0.56
     stag
    -0.56
     Adjust
    -0.56
     whistleblower
    -0.55
     bulletin
    -0.55
    POSITIVE LOGITS
    apy
    1.37
    oths
    1.25
    aps
    1.20
    iled
    1.20
    bered
    1.07
    vi
    1.04
    iling
    1.03
    pping
    1.01
    aring
    1.00
    ire
    0.99
    Activations Density 0.036%

    No Known Activations