© 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. 6100
    Prev
    Next
    INDEX
    Explanations

    comparisons between costs and benefits

    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
    1253
    +0.12
    0.4%
    876
    +0.12
    0.3%
    334
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.12
    0.05
    1965
    +0.12
    0.04
    1672
    +0.09
    0.03
    Negative Logits
     Juf
    -1.58
     inder
    -1.56
     fte
    -1.54
     inev
    -1.53
     fta
    -1.51
     secon
    -1.51
     thut
    -1.49
     volunte
    -1.47
     emphat
    -1.47
     aen
    -1.45
    POSITIVE LOGITS
     benefits
    0.76
     outweigh
    0.75
     costs
    0.73
     cost
    0.71
     worth
    0.66
     benefit
    0.65
    <bos>
    0.65
    </tfoot>
    0.64
    thinkable
    0.63
     savings
    0.63
    Activations Density 0.532%

    No Known Activations