© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4856
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific environmental business consultancy firm

    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
    50
    +0.28
    1.2%
    184
    +0.12
    0.5%
    776
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.28
    0.06
    783
    +0.12
    0.07
    184
    +0.11
    -0.02
    Negative Logits
    <bos>
    -2.82
    Autoritní
    -0.86
    ///**
    -0.82
    GEBURTSDATUM
    -0.80
     Administrativna
    -0.80
     AssemblyCompany
    -0.79
    SharedDtor
    -0.75
    Билгалдахарш
    -0.74
    Vidite
    -0.74
     وتسجيلات
    -0.73
    POSITIVE LOGITS
     maneu
    1.33
     unlaw
    1.19
     affor
    1.19
     impra
    1.18
     increa
    1.18
     reluct
    1.17
     inev
    1.14
     disagre
    1.11
     accla
    1.10
     guarante
    1.07
    Activations Density 1.658%

    No Known Activations