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. 15906
    Prev
    Next
    INDEX
    Explanations

    references to expertise or being an expert in a particular field

    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
    752
    +0.22
    0.7%
    50
    +0.17
    0.5%
    605
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.22
    0.07
    16
    +0.17
    0.07
    605
    +0.14
    0.02
    Negative Logits
    <bos>
    -0.69
    ==""){
    -0.68
     kontinu
    -0.66
    =="")
    -0.64
    OrEmpty
    -0.63
    DockStyle
    -0.60
    +":
    -0.60
     typelib
    -0.59
    !="")
    -0.59
     --;
    -0.58
    POSITIVE LOGITS
     endom
    1.10
     LIRE
    1.06
     réal
    1.04
     prét
    1.04
     appré
    1.04
     vogli
    1.00
     Février
    1.00
     réuss
    0.99
     étend
    0.98
     affez
    0.97
    Activations Density 0.384%

    No Known Activations