© 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. 13440
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports statistics

    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
    2034
    +0.15
    0.5%
    1967
    +0.15
    0.5%
    1741
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.15
    0.06
    382
    +0.15
    0.07
    1757
    +0.12
    0.06
    Negative Logits
     mef
    -2.26
     dispen
    -2.22
     dises
    -2.19
     fta
    -2.17
     ?...
    -2.14
     sii
    -2.09
     effe
    -2.07
     squa
    -2.06
     ivi
    -2.03
     nece
    -2.02
    POSITIVE LOGITS
     but
    1.13
     so
    1.00
     because
    1.00
     yeah
    0.98
     I
    0.97
     and
    0.97
     or
    0.96
     which
    0.95
     if
    0.95
     maybe
    0.93
    Activations Density 0.329%

    No Known Activations