© 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. 4247
    Prev
    Next
    INDEX
    Explanations

    references to client-side configurations or settings

    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
    2004
    +0.17
    0.6%
    168
    +0.15
    0.6%
    204
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2004
    +0.17
    0.03
    168
    +0.15
    0.03
    204
    +0.14
    0.02
    Negative Logits
     madonna
    -1.80
     Mlle
    -1.75
     ?...
    -1.68
     disgra
    -1.68
     affor
    -1.68
     Abbé
    -1.67
     snoopy
    -1.67
     milf
    -1.65
     increa
    -1.64
     reluct
    -1.64
    POSITIVE LOGITS
     client
    1.67
     clients
    1.59
    client
    1.55
     Client
    1.52
    Client
    1.48
    clients
    1.38
     Clients
    1.36
    CLIENT
    1.35
    getClient
    1.28
    Clients
    1.27
    Activations Density 0.049%

    No Known Activations