© 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. 11011
    Prev
    Next
    INDEX
    Explanations

    words related to legal and corporate matters

    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
    1013
    +0.13
    0.4%
    2034
    +0.10
    0.3%
    2030
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2030
    +0.13
    0.05
    270
    +0.10
    0.05
    111
    +0.08
    0.04
    Negative Logits
     fep
    -0.99
     „,
    -0.93
     perfon
    -0.91
     fta
    -0.89
     lii
    -0.88
     ftu
    -0.88
     greate
    -0.87
     fte
    -0.82
     fuf
    -0.81
     fto
    -0.80
    POSITIVE LOGITS
     rallado
    0.58
    rlrl
    0.55
     asado
    0.50
    之一
    0.49
     geworden
    0.49
     ElementRef
    0.49
    WithMany
    0.48
     fraiche
    0.47
     varanda
    0.47
     göm
    0.47
    Activations Density 0.410%

    No Known Activations