© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5251
    Prev
    Next
    INDEX
    Explanations

    financial/economic terms and conditions

    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
    24
    +0.10
    0.3%
    468
    +0.10
    0.3%
    964
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.10
    0.04
    468
    +0.10
    0.04
    1324
    +0.07
    0.04
    Negative Logits
     inev
    -1.53
     emphat
    -1.52
     guarante
    -1.49
     effe
    -1.49
     increa
    -1.48
     fuf
    -1.48
     accla
    -1.45
     fta
    -1.43
     thut
    -1.42
     reluct
    -1.41
    POSITIVE LOGITS
     worse
    0.87
     conditions
    0.81
     situation
    0.80
     condition
    0.77
    conditions
    0.72
     improving
    0.72
     improvement
    0.72
     worst
    0.72
     improve
    0.70
     worsen
    0.70
    Activations Density 0.316%

    No Known Activations