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. 14025
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical restraint and confinement

    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
    1385
    +0.12
    0.4%
    416
    +0.11
    0.3%
    683
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    416
    +0.12
    0.05
    736
    +0.11
    0.05
    1352
    +0.09
    0.04
    Negative Logits
     palab
    -0.87
     lele
    -0.86
     kram
    -0.85
     hina
    -0.84
     alkoh
    -0.83
     lemp
    -0.83
     haup
    -0.83
     vito
    -0.83
     gius
    -0.82
     doman
    -0.82
    POSITIVE LOGITS
     tight
    0.71
     binding
    0.69
     binds
    0.67
     rope
    0.66
     tighter
    0.65
     restraints
    0.64
     tightened
    0.63
     straps
    0.63
     tying
    0.63
     ropes
    0.63
    Activations Density 0.260%

    No Known Activations