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. 18233
    Prev
    Next
    INDEX
    Explanations

    short phrases related to advice-giving

    oai_token-act-pair · gpt-3.5-turbo

    queries and phrases related to seeking or giving advice

    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
    bill
    -0.83
    atsu
    -0.69
    tions
    -0.69
     Canad
    -0.68
    edly
    -0.67
    Eye
    -0.67
    AU
    -0.65
    FN
    -0.65
    atem
    -0.65
    APH
    -0.64
    POSITIVE LOGITS
     aspiring
    1.17
     readers
    1.07
     beginners
    1.02
     listeners
    0.86
     policymakers
    0.83
     youngsters
    0.82
     coping
    0.81
     learners
    0.79
     future
    0.79
     navigating
    0.79
    Activations Density 0.303%

    No Known Activations