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. 15578
    Prev
    Next
    INDEX
    Explanations

    event information, such as locations, dates, and descriptions

    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
    674
    +0.11
    0.3%
    939
    +0.09
    0.3%
    856
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    935
    +0.11
    0.02
    856
    +0.09
    0.03
    1473
    +0.09
    0.02
    Negative Logits
     getAge
    -0.78
     heapq
    -0.78
     unwarran
    -0.74
     tanong
    -0.70
     smtplib
    -0.70
    YECTO
    -0.68
     pymysql
    -0.66
    XmlEnum
    -0.66
     tolerably
    -0.66
     BIBSYS
    -0.63
    POSITIVE LOGITS
    <bos>
    0.54
     familières
    0.46
     éven
    0.46
    Παραπομπές
    0.46
     geomé
    0.46
    weekend
    0.45
     cittad
    0.45
     Paglinawan
    0.44
     poveznice
    0.44
    consulté
    0.43
    Activations Density 0.092%

    No Known Activations