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. 830
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrange" and its variations in various contexts

    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
    +0.21
    1.2%
    1872
    +0.14
    0.7%
    1548
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.21
    0.02
    1548
    +0.14
    0.01
    1092
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.66
    echo
    -0.67
    ComponentModel
    -0.66
    meta
    -0.66
    InjectMocks
    -0.65
    CreateMap
    -0.65
    public
    -0.65
    cdk
    -0.64
    api
    -0.64
    Meta
    -0.63
    POSITIVE LOGITS
     milf
    2.11
     maneu
    2.01
     stockholm
    1.90
     hentai
    1.89
     madonna
    1.85
     jurassic
    1.84
     shenan
    1.83
     reluct
    1.82
     disagre
    1.81
     snoopy
    1.80
    Activations Density 0.039%

    No Known Activations