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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10915
    Prev
    Next
    INDEX
    Explanations

    phrases related to encouragement to try something or give it a chance

    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
    991
    +0.11
    0.3%
    674
    +0.10
    0.3%
    1413
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    991
    +0.11
    0.03
    865
    +0.10
    0.02
    871
    +0.08
    0.02
    Negative Logits
     maneu
    -1.44
     depic
    -1.39
     inappro
    -1.36
     shenan
    -1.35
     indestru
    -1.34
     reluct
    -1.33
     disagre
    -1.33
     affor
    -1.31
     sophistic
    -1.30
     emphat
    -1.30
    POSITIVE LOGITS
    <bos>
    0.83
    give
    0.69
     pagkak
    0.67
     give
    0.63
    given
    0.58
     itong
    0.57
    stateParams
    0.57
     GIVE
    0.57
     iprot
    0.56
    Give
    0.55
    Activations Density 0.116%

    No Known Activations