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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 737
    Prev
    Next
    INDEX
    Explanations

    websites with images and videos

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1777
    +0.24
    1.3%
    204
    +0.16
    0.8%
    228
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.24
    0.06
    1363
    +0.16
    0.04
    1777
    +0.15
    0.04
    Negative Logits
     himo
    -0.61
    IonicModule
    -0.54
     jsPsych
    -0.54
    addCriterion
    -0.53
     يتيمه
    -0.51
    Serviço
    -0.51
     مرئيه
    -0.50
    données
    -0.50
    MAXN
    -0.50
     def
    -0.50
    POSITIVE LOGITS
     reluct
    1.02
     indestru
    0.96
     apprehen
    0.95
     maneu
    0.94
     volunte
    0.92
     accla
    0.90
     jorge
    0.89
     shenan
    0.89
     reconno
    0.87
     encomp
    0.85
    Activations Density 0.575%

    No Known Activations