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. 15275
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific publication, The Guardian

    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
    795
    +0.15
    0.6%
    1618
    +0.15
    0.6%
    1741
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    795
    +0.15
    0.02
    1493
    +0.15
    0.01
    214
    +0.14
    0.01
    Negative Logits
    ôtel
    -0.57
    tagHelperRunner
    -0.48
    requipa
    -0.48
    äsident
    -0.47
    flé
    -0.46
    CardBody
    -0.45
     esternos
    -0.45
    larged
    -0.44
    losseum
    -0.44
    PILE
    -0.44
    POSITIVE LOGITS
     Guardian
    1.29
    Guardian
    1.24
     guardian
    1.08
     Guardians
    1.08
    guardian
    1.07
    theguardian
    1.00
     guardians
    0.93
    Guardians
    0.90
     GUARD
    0.85
    GUARD
    0.74
    Activations Density 0.105%

    No Known Activations