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. 2903
    Prev
    Next
    INDEX
    Explanations

    contact information in an email format

    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
    1343
    +0.17
    0.5%
    736
    +0.11
    0.3%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.02
    294
    +0.11
    0.01
    782
    +0.10
    0.02
    Negative Logits
     Pyrene
    -0.79
     chery
    -0.79
     claudia
    -0.73
     tolerably
    -0.71
     fua
    -0.70
     budapest
    -0.69
     wien
    -0.69
     pyridine
    -0.68
     vainly
    -0.68
     mallorca
    -0.67
    POSITIVE LOGITS
    >@
    0.66
    asteroide
    0.63
     conva
    0.62
    .@
    0.62
     conclud
    0.61
    -@
    0.61
     solidar
    0.61
     riten
    0.60
    Interess
    0.60
     $@
    0.59
    Activations Density 0.033%

    No Known Activations