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. 15862
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical values

    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
    2036
    +0.12
    0.4%
    196
    +0.10
    0.3%
    814
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.12
    0.06
    2036
    +0.10
    0.05
    147
    +0.10
    0.03
    Negative Logits
    Šaltiniai
    -0.77
    Nuorodos
    -0.62
    Enllaços
    -0.62
    CascadeType
    -0.54
    blico
    -0.53
    Referencer
    -0.52
    ManagedBean
    -0.52
     nawr
    -0.51
    Pautan
    -0.51
    ModelAdmin
    -0.51
    POSITIVE LOGITS
     bangkok
    0.66
     beverly
    0.62
     Confu
    0.61
     guatemala
    0.60
     pamph
    0.59
     pym
    0.58
     Moslem
    0.58
     santana
    0.57
     hilton
    0.57
     chevrolet
    0.56
    Activations Density 0.309%

    No Known Activations