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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12363
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or official matters

    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
    1253
    +0.11
    0.3%
    872
    +0.09
    0.2%
    766
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1785
    +0.11
    0.03
    1984
    +0.09
    0.03
    1555
    +0.08
    0.03
    Negative Logits
     berea
    -1.07
     reluct
    -1.07
     apprehen
    -1.05
     ineffec
    -1.05
     wherea
    -1.03
     impra
    -0.99
     accla
    -0.98
     pamph
    -0.98
     shenan
    -0.98
     intersper
    -0.97
    POSITIVE LOGITS
     anybody
    0.80
     anyone
    0.75
    Anyone
    0.73
    anyone
    0.73
     beginnetje
    0.70
    iconque
    0.69
    Anybody
    0.68
     reasonable
    0.65
     anywhere
    0.64
     Anyone
    0.63
    Activations Density 0.286%

    No Known Activations