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. 2304
    Prev
    Next
    INDEX
    Explanations

    medical conditions and symptoms

    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
    1577
    +0.35
    1.4%
    599
    +0.30
    1.2%
    1842
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.35
    0.08
    599
    +0.30
    0.17
    612
    +0.18
    -0.01
    Negative Logits
     encomp
    -0.75
     indestru
    -0.71
    <bos>
    -0.70
     benevol
    -0.67
     viciss
    -0.66
     abito
    -0.65
     abbra
    -0.65
     autorytatywna
    -0.65
     papà
    -0.63
     aspetta
    -0.62
    POSITIVE LOGITS
    Попис
    0.51
    TextWatcher
    0.48
    MessageTagHelper
    0.44
    QtWidgets
    0.40
    dollis
    0.38
    thargy
    0.38
    rimid
    0.36
    ércoles
    0.35
    NameValuePair
    0.35
    LabelTagHelper
    0.35
    Activations Density 4.648%

    No Known Activations