© 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. 6265
    Prev
    Next
    INDEX
    Explanations

    words related to friendliness or being friendly

    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
    1145
    +0.17
    0.6%
    920
    +0.12
    0.4%
    1763
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1145
    +0.17
    0.03
    2030
    +0.12
    0.02
    538
    +0.12
    0.02
    Negative Logits
    wieś
    -0.60
    DropColumn
    -0.58
    Arqu
    -0.56
    mistak
    -0.56
    Alguna
    -0.55
    Доброго
    -0.55
    FlatAppearance
    -0.54
    zewod
    -0.53
    Dado
    -0.53
    SwitchCompat
    -0.53
    POSITIVE LOGITS
     friendly
    1.05
     Friendly
    1.00
     friendliness
    0.94
    Friendly
    0.94
    friendly
    0.91
     unfriendly
    0.90
     jaya
    0.86
     tew
    0.78
     territo
    0.77
     exciter
    0.77
    Activations Density 0.111%

    No Known Activations