© 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. 12067
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking actions

    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
    251
    +0.11
    0.4%
    1140
    +0.11
    0.4%
    410
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.11
    0.07
    1140
    +0.11
    0.07
    61
    +0.10
    0.06
    Negative Logits
    definecolor
    -0.63
    openSession
    -0.63
    "}";
    -0.59
    Aún
    -0.56
     TextFormField
    -0.56
    StatusBadRequest
    -0.56
    OutputType
    -0.55
    dinga
    -0.53
    liminaries
    -0.53
    bindParam
    -0.52
    POSITIVE LOGITS
     strick
    1.52
     increa
    1.46
     fuf
    1.44
     encomp
    1.35
     effe
    1.34
     impra
    1.34
     affor
    1.33
     ?...
    1.32
     scrat
    1.30
     suscep
    1.30
    Activations Density 0.155%

    No Known Activations