© 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. 0-RES-JB
    11. 2693
    Prev
    Next
    INDEX
    Explanations

    phrases related to states

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.12
    0.6%
    1323
    +0.06
    0.3%
    1127
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.12
    0.07
    2
    +0.06
    0.06
    734
    +0.05
    0.06
    Negative Logits
    <bos>
    -1.86
     continue
    -0.80
     expand
    -0.76
     accept
    -0.76
     prevent
    -0.73
     do
    -0.73
     become
    -0.73
     eliminate
    -0.73
     earn
    -0.73
    .
    -0.72
    POSITIVE LOGITS
     stockholm
    2.11
     affor
    2.08
     maneu
    2.03
     wien
    2.01
     lyon
    2.01
     fta
    1.99
     Juf
    1.97
     Etat
    1.97
     aen
    1.97
     accla
    1.96
    Activations Density 0.094%

    No Known Activations