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. 15898
    Prev
    Next
    INDEX
    Explanations

    financial-related information

    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
    1870
    +0.16
    0.5%
    764
    +0.14
    0.4%
    678
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.16
    0.05
    764
    +0.14
    0.06
    678
    +0.10
    0.07
    Negative Logits
     termica
    -0.64
    XmlAccessType
    -0.61
    FormTagHelper
    -0.56
    EndInit
    -0.56
    AlterField
    -0.54
     vettoriale
    -0.53
    enetrable
    -0.52
     esterno
    -0.52
    RemoveField
    -0.51
     esterna
    -0.51
    POSITIVE LOGITS
    <bos>
    0.59
     topics
    0.59
     pymysql
    0.56
     pymongo
    0.56
     enthusiast
    0.53
     Independiente
    0.53
     pylab
    0.52
     Compañ
    0.52
     interesan
    0.51
     texinfo
    0.50
    Activations Density 0.576%

    No Known Activations