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. 424
    Prev
    Next
    INDEX
    Explanations

    medical concepts and disorders, specifically related to psychiatric conditions

    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
    630
    +0.10
    0.3%
    509
    +0.10
    0.3%
    1553
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.10
    0.01
    630
    +0.10
    0.04
    509
    +0.09
    0.07
    Negative Logits
    mberto
    -0.62
    DockStyle
    -0.48
     $#
    -0.47
     utop
    -0.47
    olybden
    -0.47
     toscana
    -0.47
    liseum
    -0.46
     Alembic
    -0.45
    lankton
    -0.45
    ssf
    -0.45
    POSITIVE LOGITS
     hoody
    0.84
     unspeak
    0.73
     psychiatric
    0.72
     hairc
    0.71
     apprehen
    0.71
     indescri
    0.69
     unwarran
    0.67
     mental
    0.66
     vainly
    0.63
     lolita
    0.63
    Activations Density 0.882%

    No Known Activations