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. 286
    Prev
    Next
    INDEX
    Explanations

    laws and legislative processes

    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
    2034
    +0.14
    0.4%
    284
    +0.10
    0.3%
    1013
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.10
    2044
    +0.10
    0.08
    1013
    +0.10
    0.07
    Negative Logits
     ?...
    -1.63
     increa
    -1.56
     !...
    -1.51
     NOO
    -1.46
     fuf
    -1.46
     aen
    -1.44
     emphat
    -1.43
     guarante
    -1.42
     unden
    -1.41
     secon
    -1.40
    POSITIVE LOGITS
     ASAP
    1.12
     asap
    1.03
     before
    0.85
     because
    0.82
     lest
    0.80
     so
    0.79
     preferably
    0.74
     regardless
    0.74
     rather
    0.73
     sooner
    0.72
    Activations Density 0.699%

    No Known Activations