© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12209
    Prev
    Next
    INDEX
    Explanations

    words related to dating methods and discoveries

    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
    1150
    +0.11
    0.3%
    1870
    +0.10
    0.3%
    1485
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.11
    0.08
    639
    +0.10
    0.07
    1095
    +0.10
    0.04
    Negative Logits
     „,
    -1.02
     aen
    -0.96
     tew
    -0.93
     lill
    -0.92
     daf
    -0.90
     fta
    -0.85
     mme
    -0.85
     lele
    -0.85
     lii
    -0.85
     mef
    -0.85
    POSITIVE LOGITS
     somewhere
    0.65
    rlrl
    0.63
     whose
    0.60
     or
    0.58
     someone
    0.58
     nào
    0.57
     somebody
    0.56
    guém
    0.54
     Someone
    0.54
    Someone
    0.54
    Activations Density 0.686%

    No Known Activations