© 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. 6184
    Prev
    Next
    INDEX
    Explanations

    actions related to doors or locks being opened or closed

    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
    1385
    +0.12
    0.4%
    906
    +0.11
    0.3%
    416
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.12
    0.04
    289
    +0.11
    0.03
    946
    +0.09
    0.04
    Negative Logits
     utop
    -1.05
     solidar
    -0.94
     ideolog
    -0.94
     kram
    -0.90
     minimalis
    -0.89
     konkre
    -0.88
     maksi
    -0.88
     vern
    -0.86
     plak
    -0.86
     alkoh
    -0.86
    POSITIVE LOGITS
     doors
    0.98
     door
    0.90
     opening
    0.85
     openings
    0.81
     opened
    0.80
    doors
    0.78
     Doors
    0.74
    Doors
    0.72
    opening
    0.72
     open
    0.70
    Activations Density 0.357%

    No Known Activations