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. 882
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of disapproval

    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
    +0.24
    1.0%
    1328
    +0.13
    0.5%
    501
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.24
    0.04
    1328
    +0.13
    0.04
    1352
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.92
     intersper
    -1.18
     amass
    -0.84
    /***
    
    -0.80
     endow
    -0.79
     disarm
    -0.77
     rouse
    -0.76
     disambigu
    -0.72
     vanqu
    -0.72
     acquaint
    -0.70
    POSITIVE LOGITS
    should
    0.85
     Should
    0.82
    Should
    0.81
     should
    0.80
     SHOULD
    0.75
    hould
    0.69
     shouldn
    0.68
    bekah
    0.60
     noten
    0.60
    cautionary
    0.60
    Activations Density 0.113%

    No Known Activations