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. 15126
    Prev
    Next
    INDEX
    Explanations

    descriptive details of events or locations

    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
    1978
    +0.15
    0.5%
    776
    +0.14
    0.4%
    1967
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    528
    +0.15
    0.05
    776
    +0.14
    0.06
    411
    +0.12
    0.05
    Negative Logits
     nadzie
    -0.84
     redhead
    -0.80
     a
    -0.79
     as
    -0.76
     in
    -0.76
     dachshund
    -0.75
     motherfucker
    -0.74
     ruddy
    -0.74
     languid
    -0.74
     at
    -0.74
    POSITIVE LOGITS
     alkoh
    2.09
     utop
    2.00
     kosme
    1.98
     silikon
    1.97
     solidar
    1.91
     kön
    1.87
     minimalis
    1.86
     keramik
    1.85
     antik
    1.81
     karton
    1.80
    Activations Density 0.193%

    No Known Activations