© 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. 1940
    Prev
    Next
    INDEX
    Explanations

    fractions or numerical ratios

    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
    757
    +0.16
    0.5%
    1892
    +0.15
    0.5%
    1328
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1892
    +0.16
    0.07
    757
    +0.15
    0.08
    1909
    +0.13
    0.06
    Negative Logits
     assailed
    -0.50
     bequeathed
    -0.49
     grumbled
    -0.49
     vainly
    -0.49
     gaily
    -0.49
     nobly
    -0.48
     whistled
    -0.48
     strode
    -0.48
     quitted
    -0.48
     triumphantly
    -0.47
    POSITIVE LOGITS
    FOR
    0.86
    for
    0.76
    For
    0.72
     FOR
    0.72
     bahay
    0.69
     loob
    0.68
     sarili
    0.67
     For
    0.64
     affatto
    0.64
     affez
    0.63
    Activations Density 0.281%

    No Known Activations