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. 1229
    Prev
    Next
    INDEX
    Explanations

    instances of the word "or" and related phrases involving options and alternatives

    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
    +0.31
    1.4%
    1806
    +0.12
    0.5%
    1127
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.31
    0.09
    1127
    +0.12
    0.08
    1472
    +0.12
    0.08
    Negative Logits
    <bos>
    -2.32
     SEDS
    -0.81
    deelte
    -0.70
    sidemargin
    -0.69
     ProtoMessage
    -0.69
    HideFlags
    -0.69
     "..\..\..\
    -0.68
    apnews
    -0.68
    Παραπομπές
    -0.67
    ⓧ
    -0.66
    POSITIVE LOGITS
     maneu
    2.02
     impra
    1.95
     increa
    1.88
     disagre
    1.88
     milf
    1.86
     affor
    1.86
     shenan
    1.82
     accla
    1.81
     reluct
    1.76
     scrat
    1.73
    Activations Density 0.252%

    No Known Activations