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. 15322
    Prev
    Next
    INDEX
    Explanations

    descriptions related to architectural structures and interior spaces

    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
    394
    +0.23
    0.8%
    184
    +0.16
    0.6%
    1224
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.23
    0.04
    599
    +0.16
    0.09
    394
    +0.15
    0.06
    Negative Logits
     dises
    -0.81
     maroc
    -0.74
     hina
    -0.73
     milano
    -0.72
     buta
    -0.72
     mariana
    -0.71
     baum
    -0.71
     vogli
    -0.71
     bandung
    -0.70
     petto
    -0.70
    POSITIVE LOGITS
    ,”
    0.84
    ,"
    0.81
    ”,
    0.69
    ,'
    0.65
    ",
    0.64
     [
    0.63
    ”
    0.63
    ,’
    0.63
    ,''
    0.60
    ,”
    0.58
    Activations Density 0.732%

    No Known Activations