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. 620
    Prev
    Next
    INDEX
    Explanations

    words related to technology and programming

    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
    •Typos

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    577
    +0.11
    0.3%
    678
    +0.10
    0.3%
    1343
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.11
    0.06
    577
    +0.10
    0.05
    138
    +0.10
    0.06
    Negative Logits
    cember
    -0.76
    becker
    -0.59
     Testamento
    -0.56
    thday
    -0.55
    ruary
    -0.54
     ‹
    -0.54
    funda
    -0.54
     rege
    -0.54
    heyd
    -0.53
    hever
    -0.53
    POSITIVE LOGITS
     quæ
    1.11
     unlaw
    1.04
     unwarran
    1.00
     liberality
    0.97
     shewn
    0.96
     repug
    0.94
     eorum
    0.92
     affatto
    0.90
     potest
    0.90
     impractica
    0.87
    Activations Density 0.463%

    No Known Activations