© 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. 4566
    Prev
    Next
    INDEX
    Explanations

    sentences expressing commitment, hard work, or taking action

    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
    1129
    +0.11
    0.3%
    1343
    +0.10
    0.3%
    344
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.11
    0.08
    599
    +0.10
    0.06
    658
    +0.10
    0.06
    Negative Logits
     impra
    -1.77
     indestru
    -1.75
     affor
    -1.68
     bordeaux
    -1.68
     increa
    -1.66
     inext
    -1.65
     secon
    -1.65
     wien
    -1.65
     desir
    -1.64
     impractica
    -1.63
    POSITIVE LOGITS
     myself
    0.99
     personally
    0.94
     BoxFit
    0.75
     my
    0.71
    StoreMessageInfo
    0.68
    myself
    0.67
    Tôi
    0.67
     am
    0.65
     personal
    0.65
    tonode
    0.64
    Activations Density 0.354%

    No Known Activations