© 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. 5622
    Prev
    Next
    INDEX
    Explanations

    phrases related to data manipulation or mathematical operations

    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
    1328
    +0.16
    0.6%
    1506
    +0.13
    0.4%
    1045
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.16
    0.04
    1506
    +0.13
    0.04
    316
    +0.12
    0.03
    Negative Logits
     guarante
    -0.97
     inappro
    -0.93
     impractica
    -0.92
     emphat
    -0.91
     affor
    -0.91
     unlaw
    -0.91
     alre
    -0.89
     increa
    -0.88
     Cfr
    -0.88
     effe
    -0.87
    POSITIVE LOGITS
    from
    0.74
     from
    0.73
    จาก
    0.65
     från
    0.60
    From
    0.60
    ffilm
    0.60
     derived
    0.60
    archiviato
    0.60
     FROM
    0.59
    derived
    0.58
    Activations Density 0.208%

    No Known Activations