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. 710
    Prev
    Next
    INDEX
    Explanations

    instances where someone jumps out of something or is startled

    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
    1805
    +0.10
    0.3%
    897
    +0.09
    0.3%
    1356
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.10
    0.03
    1356
    +0.09
    0.02
    1805
    +0.09
    0.02
    Negative Logits
    Δείτε
    -0.49
    cense
    -0.47
    圭
    -0.46
    rencies
    -0.46
     ladrillo
    -0.43
    徊
    -0.43
     Läs
    -0.43
     Contribu
    -0.43
     運
    -0.42
    `)
    -0.41
    POSITIVE LOGITS
     unwarran
    0.85
     pymysql
    0.76
     nece
    0.74
     anhyd
    0.73
     ftu
    0.70
     plenti
    0.69
     emphat
    0.69
     foon
    0.69
     leaped
    0.68
     cytoplas
    0.68
    Activations Density 0.137%

    No Known Activations