© 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. 10566
    Prev
    Next
    INDEX
    Explanations

    references to sports injuries

    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
    906
    +0.13
    0.4%
    1967
    +0.10
    0.3%
    856
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.13
    0.03
    223
    +0.10
    0.03
    1439
    +0.08
    0.04
    Negative Logits
     swarovski
    -0.96
    jectures
    -0.93
     particolar
    -0.86
     virtù
    -0.82
     anhyd
    -0.81
     pollut
    -0.79
     Février
    -0.78
     compleanno
    -0.77
     effe
    -0.76
     paradiso
    -0.76
    POSITIVE LOGITS
     weekend
    0.58
     Saturday
    0.56
     clash
    0.55
     games
    0.54
     Gorb
    0.50
     nettement
    0.50
     Sunday
    0.50
     inaugu
    0.49
     subgoal
    0.48
     week
    0.48
    Activations Density 0.308%

    No Known Activations