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. 706
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "malice" or negative traits

    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
    795
    +0.17
    1.1%
    50
    +0.15
    0.9%
    971
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    795
    +0.17
    0.03
    1622
    +0.15
    0.02
    1331
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.43
    Географи
    -0.70
    setDo
    -0.70
    AutoScaleMode
    -0.68
    Петербург
    -0.65
     AppCompatTheme
    -0.64
    UseVisualStyle
    -0.63
    Hướng
    -0.63
    mergeFrom
    -0.62
    <tfoot>
    -0.62
    POSITIVE LOGITS
     thut
    1.72
     ftu
    1.62
     perfon
    1.60
     effe
    1.60
     reft
    1.59
     wien
    1.59
     sovere
    1.55
     stockholm
    1.53
     Augu
    1.52
     §.
    1.52
    Activations Density 0.065%

    No Known Activations