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. 16080
    Prev
    Next
    INDEX
    Explanations

    Twitter handles

    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
    1105
    +0.08
    0.3%
    650
    +0.08
    0.2%
    1343
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1105
    +0.08
    0.03
    1269
    +0.08
    0.02
    915
    +0.07
    0.02
    Negative Logits
    Glej
    -0.66
    ximadamente
    -0.58
    Și
    -0.53
    ánto
    -0.53
    cektir
    -0.53
     Alamofire
    -0.52
    Vegeu
    -0.52
    Denote
    -0.51
    jątk
    -0.51
    aniline
    -0.50
    POSITIVE LOGITS
    twitter
    1.17
     twitter
    1.03
     Twitter
    0.92
    Twitter
    0.90
     TWITTER
    0.88
    twimg
    0.80
     Tweets
    0.79
     Twit
    0.79
     tweets
    0.77
     tweet
    0.77
    Activations Density 0.030%

    No Known Activations