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. 1421
    Prev
    Next
    INDEX
    Explanations

    phrases related to the preservation and documentation of information or evidence

    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
    1173
    +0.10
    0.3%
    490
    +0.08
    0.2%
    382
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.10
    0.04
    1173
    +0.08
    0.04
    257
    +0.08
    0.04
    Negative Logits
    kram
    -0.68
     épu
    -0.68
     prét
    -0.67
    !!</
    -0.67
     habet
    -0.65
     élar
    -0.65
    UwU
    -0.63
     éto
    -0.63
     quæ
    -0.63
     rassemble
    -0.61
    POSITIVE LOGITS
     placed
    0.74
     examined
    0.74
     kept
    0.73
     taken
    0.71
     replaced
    0.68
     handled
    0.68
     brought
    0.68
     analysed
    0.68
     inspected
    0.68
     cared
    0.68
    Activations Density 0.306%

    No Known Activations