Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 202
    Prev
    Next
    INDEX
    Explanations

    mentions of violent behavior and legal proceedings

    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
    604
    +0.11
    0.3%
    906
    +0.10
    0.3%
    1201
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.06
    100
    +0.10
    0.05
    972
    +0.08
    0.04
    Negative Logits
     haup
    -1.15
     prodi
    -1.04
     fup
    -1.02
     franz
    -1.02
     lele
    -1.02
     sii
    -0.99
     kasa
    -0.99
     daz
    -0.97
     mef
    -0.97
     fign
    -0.96
    POSITIVE LOGITS
     violence
    0.76
     retali
    0.65
     violent
    0.64
     aggression
    0.63
     retaliation
    0.62
     provoked
    0.60
     altercation
    0.58
     anger
    0.57
     revenge
    0.56
     incident
    0.56
    Activations Density 0.792%

    No Known Activations