© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5525
    Prev
    Next
    INDEX
    Explanations

    text related to philosophical and theoretical discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1577
    +0.47
    1.8%
    394
    +0.16
    0.6%
    50
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.47
    0.21
    163
    +0.16
    0.05
    184
    +0.15
    0.01
    Negative Logits
     reluct
    -1.21
     depic
    -1.14
     emphat
    -1.11
     simplif
    -1.10
     intersper
    -1.10
     increa
    -1.08
     encomp
    -1.07
     disagre
    -1.07
     guarante
    -1.04
     fuf
    -1.03
    POSITIVE LOGITS
    <>
    0.49
     others
    0.47
     decisions
    0.44
     دیگران
    0.42
     outcomes
    0.41
    BagConstraints
    0.41
    >
    0.41
    newVal
    0.41
    JMenuBar
    0.41
     things
    0.41
    Activations Density 4.778%

    No Known Activations