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. 15879
    Prev
    Next
    INDEX
    Explanations

    mentions of historical or significant events involving various individuals or countries

    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
    1667
    +0.08
    0.2%
    1013
    +0.07
    0.2%
    1241
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1436
    +0.08
    0.05
    54
    +0.07
    0.04
    427
    +0.07
    0.05
    Negative Logits
    Referencie
    -0.58
    Iné
    -0.52
    Litteratur
    -0.52
    Linki
    -0.52
    Zobacz
    -0.51
    __.__
    -0.50
     jesteś
    -0.48
    Kilder
    -0.48
    Bardzo
    -0.47
    IBOutlet
    -0.47
    POSITIVE LOGITS
     swarovski
    0.84
     milano
    0.80
     hcm
    0.80
     pecuni
    0.79
     Simult
    0.79
     palio
    0.77
     cannes
    0.77
     murano
    0.76
     anello
    0.75
     silikon
    0.75
    Activations Density 0.424%

    No Known Activations