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. 2931
    Prev
    Next
    INDEX
    Explanations

    information related to city infrastructure development projects

    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
    161
    +0.13
    0.4%
    752
    +0.13
    0.4%
    1334
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.13
    0.06
    161
    +0.13
    0.05
    1892
    +0.13
    0.04
    Negative Logits
    ECTION
    -0.57
    DisplayMetrics
    -0.55
    zeiti
    -0.50
    getLogin
    -0.49
    copyOf
    -0.48
    mode
    -0.48
    emptyList
    -0.48
     daleko
    -0.47
    ruitment
    -0.47
    asString
    -0.47
    POSITIVE LOGITS
     hcm
    0.97
     reluct
    0.88
     Augu
    0.88
     unve
    0.86
     impra
    0.81
     Simult
    0.80
     Confu
    0.80
     viciss
    0.78
     ecru
    0.76
     excru
    0.75
    Activations Density 0.256%

    No Known Activations