© 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. 4617
    Prev
    Next
    INDEX
    Explanations

    pairs of closely related words or phrases in the text

    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
    872
    +0.18
    0.6%
    2015
    +0.10
    0.3%
    764
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.18
    0.07
    1380
    +0.10
    0.01
    2005
    +0.08
    0.03
    Negative Logits
    UnusedPrivate
    -0.63
    Ekster
    -0.58
     Journ
    -0.56
    Opin
    -0.55
    RegressionTest
    -0.51
    Xar
    -0.48
    WireFormatLite
    -0.48
    Sklici
    -0.47
     Cryst
    -0.46
    getKeyCode
    -0.45
    POSITIVE LOGITS
     :'(
    0.70
     stickied
    0.68
     vogli
    0.67
     :)))
    0.66
     ;-;
    0.65
     underval
    0.64
    !:)
    0.64
     ?...
    0.64
     fundos
    0.63
     attemp
    0.63
    Activations Density 0.569%

    No Known Activations