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. 10016
    Prev
    Next
    INDEX
    Explanations

    medical terms related to diseases and disorders

    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
    764
    +0.34
    1.5%
    50
    +0.32
    1.4%
    599
    +0.23
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.34
    0.07
    599
    +0.32
    0.06
    50
    +0.23
    0.06
    Negative Logits
    <bos>
    -1.67
    SourceChecksum
    -0.76
    parsedMessage
    -0.72
    verwijspagina
    -0.70
     nahilalakip
    -0.70
     jScrollPane
    -0.62
     Wikimédia
    -0.59
    Referències
    -0.59
    rungsseite
    -0.58
    Panamoan
    -0.58
    POSITIVE LOGITS
     unlaw
    1.38
     unspeak
    1.35
     affor
    1.23
     pamph
    1.21
     apprehen
    1.21
     tolerably
    1.21
     maneu
    1.21
     shenan
    1.20
     philanth
    1.19
     disagre
    1.18
    Activations Density 0.559%

    No Known Activations