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. 3879
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or events

    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
    •time

    No Comments

    Negative Logits
    egu
    -0.64
     Seym
    -0.61
    neath
    -0.61
     Downs
    -0.60
    chuk
    -0.59
    luster
    -0.59
     Vaugh
    -0.56
     Berman
    -0.56
     Schneider
    -0.55
    aky
    -0.55
    POSITIVE LOGITS
    llular
    0.72
    actionDate
    0.72
     async
    0.68
    NetMessage
    0.64
    soType
    0.61
     html
    0.61
    SourceFile
    0.60
     ·
    0.60
     partName
    0.60
    ihad
    0.58
    Activations Density 0.119%

    No Known Activations