© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3469
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal habits or routines

    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
    876
    +0.09
    0.2%
    690
    +0.08
    0.2%
    674
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.09
    0.02
    2044
    +0.08
    0.05
    1497
    +0.07
    0.02
    Negative Logits
     Juf
    -1.76
     Khart
    -1.63
     Keny
    -1.61
     Augu
    -1.55
     secon
    -1.53
     embra
    -1.48
     fte
    -1.45
     fei
    -1.44
     Abbé
    -1.44
     Ruman
    -1.44
    POSITIVE LOGITS
     better
    0.92
     avoid
    0.88
     avoids
    0.87
     allows
    0.87
     easier
    0.84
     ensures
    0.84
     allow
    0.79
     safer
    0.78
     ensure
    0.78
     gives
    0.76
    Activations Density 0.334%

    No Known Activations