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. 1589
    Prev
    Next
    INDEX
    Explanations

    technical information related to high-speed travel and materials capable of withstanding extreme temperatures

    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
    876
    +0.14
    0.4%
    283
    +0.10
    0.3%
    872
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1953
    +0.14
    0.03
    375
    +0.10
    0.04
    1488
    +0.09
    0.05
    Negative Logits
     Keny
    -0.94
     Immig
    -0.90
     condol
    -0.86
     accla
    -0.84
     Mlle
    -0.82
     Abbé
    -0.79
     Rois
    -0.79
     pamph
    -0.78
     Hieronymus
    -0.77
     philanth
    -0.77
    POSITIVE LOGITS
     hurdle
    0.57
     hurdles
    0.56
    XmlEnum
    0.56
     feasibility
    0.55
     scalability
    0.53
     desafios
    0.53
     technologies
    0.52
     LIMITATIONS
    0.52
     expensive
    0.51
    fizierung
    0.50
    Activations Density 0.371%

    No Known Activations