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. 10042
    Prev
    Next
    INDEX
    Explanations

    mentions of specific items or practices, possibly related to conventions, promotion, or certain behaviors

    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
    871
    +0.14
    0.6%
    481
    +0.14
    0.5%
    1194
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.14
    0.05
    871
    +0.14
    0.04
    1174
    +0.12
    0.03
    Negative Logits
     volunte
    -0.73
     šte
    -0.70
     excu
    -0.67
     desir
    -0.67
     viciss
    -0.66
     disagre
    -0.65
     reluct
    -0.65
     inev
    -0.65
     depic
    -0.64
     resear
    -0.63
    POSITIVE LOGITS
     prop
    1.06
    prop
    1.02
     pro
    0.99
     PRO
    0.98
     Pro
    0.98
    PRO
    0.96
    Pro
    0.95
    pro
    0.95
     Prop
    0.94
    Prop
    0.92
    Activations Density 0.223%

    No Known Activations