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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15651
    Prev
    Next
    INDEX
    Explanations

    words related to challenges and complexities in specific situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.12
    0.4%
    776
    +0.12
    0.4%
    50
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.12
    0.04
    1820
    +0.12
    0.03
    776
    +0.12
    0.05
    Negative Logits
    timately
    -0.74
    :"-
    -0.59
    InjectAttribute
    -0.52
     tuong
    -0.52
     protoimpl
    -0.50
     createSlice
    -0.50
     Precambrian
    -0.50
    terday
    -0.49
    <()>
    -0.49
     nguyen
    -0.48
    POSITIVE LOGITS
    Nossa
    0.58
    Merken
    0.56
    Tja
    0.55
    Kontra
    0.51
    Buona
    0.51
     كومونز
    0.50
    Stap
    0.50
    Servus
    0.49
    Köln
    0.47
     AVEC
    0.47
    Activations Density 0.358%

    No Known Activations