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. 10-RES-JB
    6. 15003
    Prev
    Next
    INDEX
    Explanations

    words related to creative acts or decisions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to creation and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.71
     waivers
    -0.68
     cyn
    -0.65
    oult
    -0.65
    side
    -0.64
     Soldier
    -0.63
     Diver
    -0.60
     Spice
    -0.60
     Ambro
    -0.59
     crane
    -0.59
    POSITIVE LOGITS
    ing
    1.28
    edly
    1.21
    es
    1.20
    encies
    1.15
    itives
    1.11
    ement
    1.09
    ences
    1.08
    ements
    1.06
    ership
    1.04
    eworks
    1.03
    Activations Density 0.060%

    No Known Activations