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. 15495
    Prev
    Next
    INDEX
    Explanations

    detailed information or investigations related to financial transactions or legal proceedings

    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
    +0.27
    0.9%
    344
    +0.15
    0.5%
    964
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.27
    0.09
    946
    +0.15
    0.14
    1380
    +0.13
    0.02
    Negative Logits
     swarovski
    -1.61
     tricot
    -1.49
     broderie
    -1.47
     ecru
    -1.41
     nutella
    -1.39
     murano
    -1.27
     peppa
    -1.27
     tupperware
    -1.27
     matel
    -1.26
     hairc
    -1.25
    POSITIVE LOGITS
     alleged
    0.68
     allegations
    0.66
     investigation
    0.66
     investigations
    0.64
     accusations
    0.64
     allegation
    0.63
     suspected
    0.62
     alleging
    0.61
     reported
    0.61
     investigating
    0.60
    Activations Density 6.293%

    No Known Activations