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. 11-RES-JB
    6. 4014
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance or necessity of something

    oai_token-act-pair · gpt-3.5-turbo

    references to plans, foundations, or concerns related to discussions and strategies

    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
    ãĤĬ
    -0.81
    hig
    -0.76
    ãĤ´
    -0.75
    NULL
    -0.71
     exting
    -0.69
    ãĤ´ãĥ³
    -0.68
    èª
    -0.61
    0002
    -0.61
    SEE
    -0.61
    Dialog
    -0.61
    POSITIVE LOGITS
     we
    1.24
     everybody
    1.15
    's
    1.10
     somebody
    1.05
     happens
    1.02
     [
    0.97
     anybody
    0.93
     I
    0.91
     you
    0.88
     they
    0.87
    Activations Density 0.272%

    No Known Activations