© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13272
    Prev
    Next
    INDEX
    Explanations

    text related to policy discussion with a focus on regulations and exceptions

    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
    1131
    +0.07
    0.2%
    307
    +0.07
    0.2%
    2027
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1580
    +0.07
    0.04
    1847
    +0.07
    0.04
    1383
    +0.07
    0.04
    Negative Logits
     depic
    -0.63
     fameux
    -0.63
     shenan
    -0.62
     Nicolai
    -0.61
     reluct
    -0.60
     intersper
    -0.60
     Bartholo
    -0.60
     McLaugh
    -0.59
     milf
    -0.59
     apprehen
    -0.58
    POSITIVE LOGITS
     rather
    1.82
    rather
    1.68
     instead
    1.49
    instead
    1.41
    Rather
    1.39
     Rather
    1.39
    Instead
    1.27
    而不是
    1.19
     Instead
    1.18
     plutôt
    1.13
    Activations Density 0.686%

    No Known Activations