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. 8-RES-JB
    6. 4434
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to formal events or actions that hold significance, particularly in legal or civic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regist
    -0.56
    ãĥ³ãĤ¸
    -0.55
     contingency
    -0.54
     LOT
    -0.53
    nai
    -0.52
     NAD
    -0.51
     consists
    -0.50
     future
    -0.48
    rylic
    -0.48
    00200000
    -0.48
    POSITIVE LOGITS
    .</
    0.87
    ().
    0.84
    .''.
    0.81
     prematurely
    0.78
    !.
    0.77
    .ãĢį
    0.76
    *.
    0.76
    .[
    0.72
    .
    0.72
    .–
    0.70
    Activations Density 0.884%

    No Known Activations