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. 15469
    Prev
    Next
    INDEX
    Explanations

    information related to encoding, determining encoding, or the importance of being certain about encoding

    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
    764
    +0.37
    1.3%
    184
    +0.27
    1.0%
    674
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.37
    0.01
    184
    +0.27
    0.00
    872
    +0.17
    0.01
    Negative Logits
    Filmo
    -0.55
    Viited
    -0.55
    Ārējās
    -0.54
     Tugend
    -0.52
    Atsauces
    -0.52
     Lein
    -0.50
    __":
    
    -0.49
    Erreferentziak
    -0.48
     Rass
    -0.46
     Kork
    -0.46
    POSITIVE LOGITS
     ecru
    1.09
     swarovski
    1.09
     hairc
    1.02
     scrat
    1.00
     softshell
    0.93
     tupperware
    0.93
     friable
    0.92
     oreo
    0.92
     tricot
    0.92
     hoody
    0.92
    Activations Density 0.010%

    No Known Activations