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. 4408
    Prev
    Next
    INDEX
    Explanations

    terms related to significant or notable events or developments

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to significant agreements, models, or achievements

    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
    tics
    -1.08
    brids
    -0.90
    ources
    -0.86
    ourning
    -0.84
    anders
    -0.82
    aves
    -0.81
    iths
    -0.80
    Ģ
    -0.80
    rosso
    -0.80
    arus
    -0.79
    POSITIVE LOGITS
     moment
    0.83
     tactic
    0.83
     attraction
    0.82
     achievement
    0.81
     item
    0.78
     of
    0.77
     employer
    0.77
     project
    0.76
     idea
    0.75
     ingredient
    0.75
    Activations Density 0.338%

    No Known Activations