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. 15285
    Prev
    Next
    INDEX
    Explanations

    technical terms, such as specific software or web addresses

    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
    776
    +0.13
    0.5%
    25
    +0.13
    0.4%
    1145
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.13
    0.04
    1339
    +0.13
    0.03
    1145
    +0.12
    0.03
    Negative Logits
    mbggenerated
    -0.58
    żdy
    -0.48
     vrijwilli
    -0.48
     lccn
    -0.44
    mediate
    -0.42
     josh
    -0.40
    izophren
    -0.39
     décrire
    -0.39
     traducciones
    -0.39
    Dung
    -0.39
    POSITIVE LOGITS
     special
    1.17
     Special
    1.11
    special
    1.09
    Special
    1.07
    SPECIAL
    1.03
     SPECIAL
    0.99
     specials
    0.92
    Especial
    0.90
    pecial
    0.86
     speciale
    0.84
    Activations Density 0.075%

    No Known Activations