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. 2906
    Prev
    Next
    INDEX
    Explanations

    references to forms of punishment, justice, and government actions in a political and historical context

    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
    479
    +0.12
    0.4%
    1548
    +0.12
    0.4%
    1047
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1548
    +0.12
    0.02
    1691
    +0.12
    0.02
    1993
    +0.10
    0.03
    Negative Logits
    OGND
    -0.67
     utop
    -0.54
     ideolog
    -0.53
     rezept
    -0.51
     kopi
    -0.50
     ceb
    -0.49
     VIAF
    -0.49
     vort
    -0.49
     protes
    -0.48
     kandid
    -0.47
    POSITIVE LOGITS
     punishment
    1.03
     punish
    1.01
     punishments
    0.99
     punished
    0.96
     Punishment
    0.95
     penalty
    0.95
     Penalty
    0.95
     punishing
    0.90
    Penalty
    0.88
     penalties
    0.88
    Activations Density 0.069%

    No Known Activations