Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13923
    Prev
    Next
    INDEX
    Explanations

    political entities and positions

    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
    +0.18
    0.6%
    283
    +0.13
    0.4%
    198
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.18
    0.07
    283
    +0.13
    0.02
    227
    +0.13
    0.07
    Negative Logits
    <bos>
    -1.17
     이미
    -0.73
     in
    -0.73
     no
    -0.71
     as
    -0.71
     is
    -0.69
     has
    -0.69
     all
    -0.68
     (
    -0.68
     at
    -0.68
    POSITIVE LOGITS
     stoff
    1.79
     immen
    1.77
     pittores
    1.73
     kram
    1.72
     socie
    1.72
     alkoh
    1.71
     Ferdin
    1.70
     kosme
    1.69
     kask
    1.67
     silikon
    1.67
    Activations Density 0.403%

    No Known Activations