Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16865
    Prev
    Next
    INDEX
    Explanations

    references to various items and events available for purchase or viewing

    oai_token-act-pair · gpt-3.5-turbo

    references to music and film-related content

    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
    Attempts
    -0.86
    achment
    -0.84
    Setup
    -0.81
    PsyNetMessage
    -0.81
    icum
    -0.80
    ItemTracker
    -0.78
    Attempt
    -0.78
    SPONSORED
    -0.76
    Initial
    -0.75
    setup
    -0.74
    POSITIVE LOGITS
     classics
    1.35
     classic
    1.28
     iconic
    1.17
     legendary
    1.16
     renowned
    1.15
     artists
    1.14
     celebrities
    1.13
     legends
    1.11
     talented
    1.08
     genres
    1.07
    Activations Density 0.418%

    No Known Activations