Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2607
    Prev
    Next
    INDEX
    Explanations

    phrases related to signing up or registering for various services or opportunities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "sign up."

    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
    wich
    -0.73
    enburg
    -0.67
    omal
    -0.64
     Pie
    -0.58
    MAT
    -0.57
    cock
    -0.56
    ĸļ
    -0.54
    iHUD
    -0.54
     Mecca
    -0.54
     Zimmer
    -0.53
    POSITIVE LOGITS
    lish
    0.78
    rights
    0.78
    à¼
    0.74
    IENCE
    0.73
    uled
    0.71
     voluntarily
    0.71
     petitions
    0.71
    etition
    0.70
    itness
    0.69
     consent
    0.68
    Activations Density 0.042%

    No Known Activations