© 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. 5933
    Prev
    Next
    INDEX
    Explanations

    terms related to tolerance and intolerance in a social or political context

    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
    1892
    +0.13
    0.5%
    313
    +0.12
    0.4%
    1334
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1892
    +0.13
    0.02
    1778
    +0.12
    0.02
    455
    +0.11
    0.01
    Negative Logits
     unlaw
    -0.72
     disgra
    -0.71
     Departement
    -0.66
     glan
    -0.65
     blin
    -0.65
     ?...
    -0.65
     Nö
    -0.65
     kram
    -0.64
     emphat
    -0.63
     NOO
    -0.62
    POSITIVE LOGITS
     tolerance
    1.41
     tolerate
    1.26
     Tolerance
    1.26
    tolerance
    1.22
     tolerant
    1.20
     toler
    1.16
     tolerated
    1.14
     Toler
    1.12
    tolerant
    1.12
    Tolerance
    1.06
    Activations Density 0.087%

    No Known Activations