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. 7-RES-JB
    6. 3039
    Prev
    Next
    INDEX
    Explanations

    sentences indicating advice or instructions

    oai_token-act-pair · gpt-3.5-turbo

    statements about health insurance and its impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     orders
    -0.76
    xual
    -0.74
     scrap
    -0.71
     McMaster
    -0.67
    iga
    -0.67
    berra
    -0.64
     AX
    -0.60
     bass
    -0.60
     maple
    -0.60
     winners
    -0.60
    POSITIVE LOGITS
    Again
    0.94
    Section
    0.93
    Unless
    0.93
    Reason
    0.92
    Sometimes
    0.91
    advertising
    0.91
    Probably
    0.88
    ccording
    0.86
    Yes
    0.85
    Everyone
    0.85
    Activations Density 0.249%

    No Known Activations