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. 4526
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement or confirmation

    oai_token-act-pair · gpt-3.5-turbo

    the word "Indeed" and its variations, indicating affirmation or confirmation

    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
    QB
    -0.67
    ocene
    -0.66
    gio
    -0.65
    ammy
    -0.62
     scrimmage
    -0.60
     bang
    -0.58
    ses
    -0.58
    issors
    -0.58
     tab
    -0.57
    Ĺ
    -0.57
    POSITIVE LOGITS
    entimes
    1.12
    forth
    0.76
    ional
    0.75
    geist
    0.75
    mares
    0.73
    arist
    0.69
    apo
    0.66
     guiActiveUn
    0.66
    rey
    0.65
    chwitz
    0.65
    Activations Density 0.044%

    No Known Activations