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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 894
    Prev
    Next
    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.3%
    1978
    +0.12
    0.6%
    1870
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.27
    0.04
    1597
    +0.12
    0.03
    283
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.74
    ⓧ
    -0.90
     AssemblyCompany
    -0.80
    styleType
    -0.75
    Trichloroethane
    -0.71
    <tfoot>
    -0.71
    ///**
    -0.71
    Dichloroethene
    -0.68
     censiti
    -0.68
    पया
    -0.68
    POSITIVE LOGITS
     practition
    1.29
     jaya
    1.14
     affor
    1.14
     Juf
    1.13
     volunte
    1.13
     increa
    1.12
     lele
    1.09
     seksi
    1.07
     unlaw
    1.05
     rodriguez
    1.05
    Activations Density 0.077%

    No Known Activations