© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 5056
    Prev
    Next
    INDEX
    Explanations

    references to the Southern Poverty Law Center and its reports or findings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    703
    +0.14
    0.6%
    341
    +0.13
    0.6%
    1983
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.06
    227
    +0.13
    0.06
    1987
    +0.13
    0.05
    Negative Logits
    <?
    -0.72
    Vlastnosti
    -0.68
     đ
    -0.65
    Obec
    -0.65
     Pourtant
    -0.63
    равда
    -0.60
    <bos>
    -0.60
    código
    -0.58
    젖
    -0.58
    strona
    -0.57
    POSITIVE LOGITS
     fath
    1.17
     fuf
    1.16
     ?...
    1.16
     napoli
    1.13
     chande
    1.10
     embra
    1.09
     emphat
    1.09
     !...
    1.07
     michelin
    1.07
     lill
    1.03
    Activations Density 0.281%

    No Known Activations