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. 670
    Prev
    Next
    INDEX
    Explanations

    references to specific organizational concepts and structures

    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
    1464
    +0.10
    0.3%
    889
    +0.09
    0.3%
    390
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1464
    +0.10
    0.03
    1218
    +0.09
    0.03
    168
    +0.09
    0.03
    Negative Logits
     čet
    -0.50
    Legături
    -0.47
     deff
    -0.47
     cocker
    -0.43
     manj
    -0.42
     michelin
    -0.40
     mickey
    -0.39
     Kenn
    -0.39
     cushi
    -0.39
     interchang
    -0.38
    POSITIVE LOGITS
     topped
    0.60
     susun
    0.58
    кобрита
    0.56
    topped
    0.56
     guma
    0.56
     faudrait
    0.55
     toppen
    0.53
     kasama
    0.53
    TemporalType
    0.52
     atop
    0.52
    Activations Density 0.105%

    No Known Activations