© 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. 5145
    Prev
    Next
    INDEX
    Explanations

    quotes and statements made in a document

    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
    1531
    +0.12
    0.3%
    604
    +0.09
    0.3%
    1919
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.12
    0.08
    1531
    +0.09
    0.05
    309
    +0.09
    0.06
    Negative Logits
     Vn
    -1.05
     alkoh
    -1.03
     secon
    -1.01
     oner
    -1.01
     mef
    -0.98
     Fasc
    -0.97
     buc
    -0.97
     tuta
    -0.97
     Ue
    -0.97
     augus
    -0.96
    POSITIVE LOGITS
     nevertheless
    0.88
     nonetheless
    0.83
     still
    0.78
     digress
    0.75
     disagreed
    0.72
     insists
    0.71
     disagrees
    0.71
     insisted
    0.70
     remained
    0.69
     couldn
    0.68
    Activations Density 0.716%

    No Known Activations