© 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. 8036
    Prev
    Next
    INDEX
    Explanations

    phrases related to ensuring accuracy or correctness

    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
    1757
    +0.19
    1.0%
    50
    +0.17
    0.9%
    1350
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1757
    +0.19
    0.11
    1350
    +0.17
    0.07
    605
    +0.15
    0.01
    Negative Logits
    <bos>
    -2.06
    Cringe
    -1.13
    Fuckin
    -1.01
    Lmfao
    -0.97
    Hahahahaha
    -0.91
    FTFY
    -0.88
    Yeet
    -0.85
     Lmao
    -0.85
    /***
    -0.84
    UwU
    -0.84
    POSITIVE LOGITS
     maroc
    1.12
     seksi
    1.07
     panik
    1.06
     kasa
    1.05
     jawa
    1.04
     Keny
    1.01
     lele
    1.00
     Shakspeare
    0.99
     teras
    0.99
     turist
    0.97
    Activations Density 3.280%

    No Known Activations