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. 15939
    Prev
    Next
    INDEX
    Explanations

    information related to specific individuals, events, and locations

    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
    1023
    +0.13
    0.4%
    1983
    +0.10
    0.3%
    528
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1023
    +0.13
    0.05
    1993
    +0.10
    0.05
    474
    +0.10
    0.04
    Negative Logits
     noten
    -0.63
     EconPapers
    -0.57
     محفوظة
    -0.56
    Revenir
    -0.53
    NOTA
    -0.52
    pexpr
    -0.49
    Trả
    -0.49
    toBe
    -0.48
    ယ်
    -0.48
    NOT
    -0.48
    POSITIVE LOGITS
     Minang
    1.20
     disagre
    1.11
     pamph
    1.09
     shenan
    1.08
     fta
    1.08
     Juf
    1.08
     Miscell
    1.05
     aen
    1.05
     inappro
    1.02
     fter
    1.01
    Activations Density 0.109%

    No Known Activations