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. 15997
    Prev
    Next
    INDEX
    Explanations

    references to event locations or venues

    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
    184
    +0.33
    1.3%
    1343
    +0.24
    0.9%
    599
    +0.24
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.33
    0.05
    1343
    +0.24
    0.07
    199
    +0.24
    0.01
    Negative Logits
     unwarran
    -0.91
     reluct
    -0.89
     apprehen
    -0.89
     impra
    -0.88
     philanth
    -0.88
     uninten
    -0.88
     tolerably
    -0.87
     maneu
    -0.87
     pamph
    -0.86
     gaily
    -0.86
    POSITIVE LOGITS
    cellor
    0.45
     lej
    0.43
     選手
    0.43
     famí
    0.41
     Junho
    0.41
    FailureListener
    0.41
     assiste
    0.41
     trattano
    0.41
    FieldBuilder
    0.40
     Agosto
    0.40
    Activations Density 0.472%

    No Known Activations