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 · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15931
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "draft", particularly in the context of sports drafts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    555
    +0.14
    0.5%
    680
    +0.14
    0.5%
    421
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1101
    +0.14
    0.02
    555
    +0.14
    0.02
    316
    +0.13
    0.02
    Negative Logits
    mbggenerated
    -0.59
    Ney
    -0.47
     Clooney
    -0.46
     Noor
    -0.45
     Rowland
    -0.45
     Hubbard
    -0.43
     Ney
    -0.43
    Ethylbenzene
    -0.42
    Välislingid
    -0.42
     GoogleFonts
    -0.42
    POSITIVE LOGITS
     draft
    1.18
     Draft
    1.11
    Draft
    1.08
    draft
    1.08
     drafts
    1.07
     DRAFT
    0.96
     drafting
    0.94
     drafted
    0.94
    DRAFT
    0.93
     Drafting
    0.84
    Activations Density 0.066%

    No Known Activations