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. 15550
    Prev
    Next
    INDEX
    Explanations

    references to active or ongoing actions or states

    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
    +0.14
    0.5%
    1865
    +0.12
    0.4%
    663
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1865
    +0.14
    0.03
    663
    +0.12
    0.02
    325
    +0.12
    0.03
    Negative Logits
     leksikon
    -0.52
    LError
    -0.46
    QUADS
    -0.45
    Jose
    -0.45
    Borrar
    -0.44
    cupa
    -0.44
    enada
    -0.44
    ositol
    -0.44
    string
    -0.43
    José
    -0.43
    POSITIVE LOGITS
     ACTIVE
    1.27
     active
    1.21
     Active
    1.19
     actives
    1.14
    active
    1.11
     intersper
    1.06
    Active
    1.05
     Inactive
    1.04
     depic
    1.04
    ACTIVE
    0.99
    Activations Density 0.065%

    No Known Activations