© 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 EvalsExportsinterp-engineNEWAPI 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. 5017
    Prev
    Next
    INDEX
    Explanations

    names or words related to competition or battling

    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
    411
    +0.18
    0.7%
    1573
    +0.16
    0.6%
    1961
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.18
    0.10
    577
    +0.16
    0.06
    678
    +0.15
    0.07
    Negative Logits
    y
    -0.79
    o
    -0.69
    i
    -0.68
    ی
    -0.68
    er
    -0.66
    s
    -0.64
    ه
    -0.61
    я
    -0.61
    e
    -0.61
    ا
    -0.61
    POSITIVE LOGITS
     sappi
    1.36
     imposs
    1.36
     suspic
    1.27
     inev
    1.26
     autob
    1.22
     pessi
    1.21
     intermitt
    1.19
     igno
    1.19
     fasc
    1.18
     fluo
    1.18
    Activations Density 0.572%

    No Known Activations