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. 1556
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to problem-solving or decision-making processes

    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
    pict
    -0.74
    listed
    -0.73
     Coff
    -0.73
    prem
    -0.73
     Born
    -0.70
    Ĺ
    -0.69
    lights
    -0.67
     Williamson
    -0.67
    Choice
    -0.65
    quickShipAvailable
    -0.65
    POSITIVE LOGITS
     reconcile
    1.32
     cope
    1.26
     interpret
    1.17
     communicate
    1.16
     allocate
    1.15
     proceed
    1.13
     capitalize
    1.12
     handle
    1.10
     integrate
    1.10
     respond
    1.10
    Activations Density 0.120%

    No Known Activations