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. 8374
    Prev
    Next
    INDEX
    Explanations

    phrases related to various combinations or choices

    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
    1921
    +0.10
    0.3%
    1133
    +0.09
    0.3%
    197
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1971
    +0.10
    0.02
    1921
    +0.09
    0.02
    1368
    +0.09
    0.02
    Negative Logits
     Souha
    -0.71
     racon
    -0.68
     sobri
    -0.65
     Chapitre
    -0.65
     viciss
    -0.63
     coerci
    -0.63
     solidar
    -0.63
    Molto
    -0.63
     Membre
    -0.63
     Áng
    -0.62
    POSITIVE LOGITS
     combination
    1.06
    combination
    0.99
     Combination
    0.92
     combinations
    0.90
    Combination
    0.86
     combinación
    0.81
     combinaison
    0.79
    combinations
    0.77
     combo
    0.75
     Kombination
    0.75
    Activations Density 0.080%

    No Known Activations