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. 11-RES-JB
    6. 19026
    Prev
    Next
    INDEX
    Explanations

    dates and events in history

    oai_token-act-pair · gpt-3.5-turbo

    instances of entities and their roles or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Others
    -0.60
     goodies
    -0.55
     thereto
    -0.53
     alike
    -0.51
    PHOTOS
    -0.51
     miscar
    -0.50
    ibles
    -0.49
     dads
    -0.49
    Enlarge
    -0.49
    politics
    -0.47
    POSITIVE LOGITS
     an
    1.27
     a
    1.22
     another
    0.89
     the
    0.75
     one
    0.73
    an
    0.69
     someone
    0.67
    another
    0.63
    a
    0.60
     something
    0.58
    Activations Density 0.994%

    No Known Activations