© 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. 10993
    Prev
    Next
    INDEX
    Explanations

    phrases involving commands or requests to do something

    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
    1334
    +0.15
    0.5%
    1415
    +0.11
    0.4%
    938
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.15
    0.06
    1415
    +0.11
    0.05
    299
    +0.10
    0.04
    Negative Logits
     fta
    -2.41
     thut
    -2.17
     ftu
    -2.12
     tew
    -2.10
     aen
    -2.08
     fte
    -2.05
     fup
    -2.04
     guarante
    -2.03
     inev
    -2.02
     desir
    -2.02
    POSITIVE LOGITS
     come
    0.86
     keep
    0.85
     stay
    0.84
     be
    0.82
     take
    0.82
     make
    0.80
     look
    0.78
     do
    0.77
     stop
    0.76
     meet
    0.75
    Activations Density 0.187%

    No Known Activations