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. 21138
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic theses and scholarly writings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ses" and its variations in different 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
     outsiders
    -0.67
     detail
    -0.64
    Wire
    -0.61
    Ò
    -0.60
     today
    -0.59
    Grid
    -0.59
     impl
    -0.58
     Wel
    -0.55
     Joe
    -0.55
     populated
    -0.55
    POSITIVE LOGITS
    ses
    4.88
    sis
    2.87
    sed
    2.50
    sing
    1.87
    sers
    1.37
    si
    1.33
    se
    1.20
    sit
    1.13
    swer
    1.07
    sa
    1.07
    Activations Density 0.014%

    No Known Activations