© 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. 13037
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent incidents and emotional reactions

    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
    1253
    +0.11
    0.3%
    1644
    +0.08
    0.2%
    92
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2007
    +0.11
    0.03
    1644
    +0.08
    0.02
    1664
    +0.07
    0.03
    Negative Logits
     ftu
    -2.08
     fta
    -2.05
     fuf
    -2.02
     increa
    -1.99
     fto
    -1.98
     »>
    -1.97
     thut
    -1.97
     fte
    -1.96
     secon
    -1.96
     embra
    -1.96
    POSITIVE LOGITS
     minor
    0.78
     mere
    0.74
    ഒ
    0.72
     insignificant
    0.72
     simple
    0.69
     trivial
    0.69
     small
    0.68
     tiny
    0.68
    стракт
    0.64
     slight
    0.62
    Activations Density 0.439%

    No Known Activations