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. 251
    Prev
    Next
    INDEX
    Explanations

    mentions of aid, assistance, or support in various contexts or scenarios

    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
    1892
    +0.19
    0.8%
    1515
    +0.14
    0.6%
    521
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1892
    +0.19
    0.03
    1515
    +0.14
    0.02
    890
    +0.13
    0.02
    Negative Logits
    حياته
    -0.53
    bl
    -0.48
     pres
    -0.47
    Bl
    -0.47
     Sc
    -0.46
    حياتها
    -0.45
    NL
    -0.45
    cb
    -0.45
    kl
    -0.45
    CB
    -0.44
    POSITIVE LOGITS
     aid
    1.12
     hentai
    1.10
     Aid
    1.03
     milf
    1.03
     lmfao
    0.99
     shenan
    0.96
     🤣🤣
    0.95
    Aid
    0.95
     Aids
    0.95
     aids
    0.94
    Activations Density 0.084%

    No Known Activations