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. 7238
    Prev
    Next
    INDEX
    Explanations

    special characters and file paths

    oai_token-act-pair · gpt-3.5-turbo

    the presence of certain symbols or characters in the text

    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
    sters
    -0.68
     buoy
    -0.64
     choked
    -0.63
     Heard
    -0.62
     veto
    -0.62
     deval
    -0.62
     tourist
    -0.61
     expense
    -0.59
     divers
    -0.59
     step
    -0.59
    POSITIVE LOGITS
    WINDOWS
    1.12
    SpaceEngineers
    1.11
    AppData
    1.04
    Program
    1.03
    Documents
    1.03
    windows
    1.02
    scripts
    0.99
    DOC
    0.98
    Windows
    0.98
    temp
    0.97
    Activations Density 0.012%

    No Known Activations