© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13853
    Prev
    Next
    INDEX
    Explanations

    sentences expressing emotions or personal feelings

    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
    1137
    +0.14
    0.5%
    1271
    +0.11
    0.4%
    410
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1137
    +0.14
    0.06
    1271
    +0.11
    0.05
    410
    +0.10
    0.04
    Negative Logits
    cde
    -0.53
     Sitten
    -0.49
    Referencer
    -0.47
    المناصب
    -0.47
    Kanpo
    -0.47
    Referências
    -0.44
    habad
    -0.43
     Datum
    -0.43
    Erreferentziak
    -0.43
    Cat
    -0.42
    POSITIVE LOGITS
     FEEL
    0.99
    Felt
    0.93
     feel
    0.93
    feel
    0.90
     felt
    0.89
    Feel
    0.87
     Felt
    0.85
     feels
    0.85
    Feels
    0.83
     Feel
    0.83
    Activations Density 0.099%

    No Known Activations