© 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. 6-RES-JB
    11. 8806
    Prev
    Next
    INDEX
    Explanations

    job titles related to executives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1637
    +0.14
    0.5%
    50
    +0.11
    0.4%
    1757
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1637
    +0.14
    0.04
    321
    +0.11
    0.04
    1778
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.16
    /***
    -0.75
    principalColumn
    -0.64
    rungsseite
    -0.64
    <?
    -0.60
    lccn
    -0.59
    InjectMocks
    -0.59
    TypedDataSet
    -0.58
     intersper
    -0.58
     XXXIII
    -0.58
    POSITIVE LOGITS
     VP
    0.77
    VP
    0.67
    GYPT
    0.57
     gård
    0.56
     Hitam
    0.54
     titulada
    0.54
    vp
    0.53
    irée
    0.52
     parco
    0.52
     bolig
    0.51
    Activations Density 0.185%

    No Known Activations