© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 783
    Prev
    Next
    INDEX
    Explanations

    phrases related to standing up for oneself or others

    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
    397
    +0.13
    0.4%
    1757
    +0.12
    0.4%
    1370
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.13
    0.02
    1370
    +0.12
    0.03
    549
    +0.12
    0.03
    Negative Logits
     apprehen
    -1.45
     disagre
    -1.44
     berea
    -1.41
     increa
    -1.41
     gaily
    -1.40
     tolerably
    -1.40
     shenan
    -1.38
     maneu
    -1.38
     impra
    -1.38
     guarante
    -1.38
    POSITIVE LOGITS
     up
    0.78
    UP
    0.73
    up
    0.72
     UP
    0.69
     stand
    0.67
    stand
    0.65
     Up
    0.65
    Up
    0.64
     against
    0.61
    ups
    0.61
    Activations Density 0.080%

    No Known Activations