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. 11-RES-JB
    6. 18046
    Prev
    Next
    INDEX
    Explanations

    phrases indicating suitability or intended use for certain products or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating suitability or design intent for various purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RIP
    -0.76
    buster
    -0.75
    ceivable
    -0.75
    listed
    -0.69
    estial
    -0.69
    ickey
    -0.68
    payer
    -0.68
    soever
    -0.67
    lost
    -0.67
    eny
    -0.66
    POSITIVE LOGITS
     beginners
    1.35
     storing
    1.12
     detecting
    1.06
     transporting
    1.02
     extracting
    0.97
     maximizing
    0.96
     attaching
    0.95
     novice
    0.93
     handling
    0.93
     dealing
    0.93
    Activations Density 0.172%

    No Known Activations