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. 15061
    Prev
    Next
    INDEX
    Explanations

    descriptions of conflicts, wars, and political or legislative actions

    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
    1967
    +0.33
    1.4%
    1577
    +0.23
    1.0%
    1166
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.33
    0.19
    198
    +0.23
    0.20
    1166
    +0.12
    0.25
    Negative Logits
    aarrggbb
    -0.70
     CiNii
    -0.70
     shewn
    -0.70
    TagMode
    -0.69
    SneakyThrows
    -0.67
    @[+][
    -0.66
     eorum
    -0.63
     meis
    -0.63
     withal
    -0.62
     PLWABN
    -0.59
    POSITIVE LOGITS
    Nth
    0.51
    jandra
    0.44
    Shortest
    0.43
    mello
    0.42
    Deny
    0.41
    Advertisements
    0.41
    showAll
    0.40
    maso
    0.40
     Conjunto
    0.40
     levante
    0.40
    Activations Density 13.188%

    No Known Activations