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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1032
    Prev
    Next
    INDEX
    Explanations

    words related to a physical altercation or injury

    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
    872
    +0.11
    0.3%
    184
    +0.09
    0.3%
    1705
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.11
    0.07
    919
    +0.09
    0.03
    1499
    +0.09
    0.07
    Negative Logits
     utop
    -0.67
     Hül
    -0.66
     alkoh
    -0.65
    avax
    -0.65
     venez
    -0.65
     antik
    -0.65
     basili
    -0.64
     tenden
    -0.63
     paralel
    -0.63
     sedi
    -0.63
    POSITIVE LOGITS
     unwarran
    1.38
     shewn
    1.23
     affor
    1.17
     impra
    1.09
     tolerably
    1.09
    Dziękuję
    1.09
     disagre
    1.07
     unspeak
    1.04
     impractica
    1.04
     increa
    1.01
    Activations Density 0.503%

    No Known Activations