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. 166
    Prev
    Next
    INDEX
    Explanations

    names with a playful or fantastical association

    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
    227
    +0.10
    0.3%
    1871
    +0.10
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.10
    1597
    +0.10
    0.04
    324
    +0.09
    0.04
    Negative Logits
     viewWillAppear
    -0.77
     viewDid
    -0.73
    viewWillAppear
    -0.66
    horesis
    -0.59
    viewDid
    -0.59
    onets
    -0.58
     onBackPressed
    -0.58
     withRouter
    -0.56
    <bos>
    -0.56
     esetén
    -0.56
    POSITIVE LOGITS
     fta
    1.49
     mef
    1.48
     ftu
    1.48
     Præ
    1.46
     Juf
    1.46
     fup
    1.44
     Augu
    1.37
     fign
    1.37
     poff
    1.35
     vns
    1.33
    Activations Density 0.643%

    No Known Activations