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. 8372
    Prev
    Next
    INDEX
    Explanations

    the word "folks"

    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
    204
    +0.18
    0.7%
    1350
    +0.16
    0.6%
    1506
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.18
    0.02
    1350
    +0.16
    0.02
    1235
    +0.14
    0.02
    Negative Logits
     rè
    -0.56
     diagon
    -0.56
     Primaria
    -0.53
     pyram
    -0.53
    sune
    -0.50
     eviden
    -0.50
     Fichier
    -0.50
     simplif
    -0.50
     priva
    -0.49
     cenar
    -0.49
    POSITIVE LOGITS
     folks
    1.18
     Folks
    1.15
    Folks
    1.09
     folk
    1.01
    folk
    0.93
     Folk
    0.86
    Folk
    0.79
    fol
    0.71
     felicity
    0.65
    FOLK
    0.65
    Activations Density 0.068%

    No Known Activations