© 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. 3043
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations, organizations, and academic degrees

    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
    411
    +0.14
    0.7%
    1222
    +0.13
    0.7%
    50
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.14
    0.02
    1363
    +0.13
    0.04
    1616
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.05
    mrow
    -0.76
    ăț
    -0.73
     হয়
    -0.73
    șit
    -0.69
    setopt
    -0.69
    țiilor
    -0.68
     canceled
    -0.68
    ാൻ
    -0.68
     betweenstory
    -0.68
    POSITIVE LOGITS
     maneu
    1.60
     shenan
    1.51
     hairc
    1.49
     disagre
    1.47
     McLaugh
    1.46
     Confu
    1.44
     increa
    1.44
     disreg
    1.43
     affor
    1.43
     excru
    1.41
    Activations Density 0.897%

    No Known Activations