© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4438
    Prev
    Next
    INDEX
    Explanations

    sports-related news content, particularly focusing on game outcomes and player performances

    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
    856
    +0.11
    0.3%
    1842
    +0.10
    0.3%
    1177
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1606
    +0.11
    0.04
    72
    +0.10
    0.04
    53
    +0.09
    0.02
    Negative Logits
    ,
    -0.68
     and
    -0.64
    .
    -0.62
    -
    -0.62
     
    -0.62
     и
    -0.60
    ，
    -0.60
    and
    -0.60
    if
    -0.60
    location
    -0.59
    POSITIVE LOGITS
     Souha
    1.78
     Juf
    1.58
     Sén
    1.44
     Keny
    1.42
     vété
    1.41
     Cfr
    1.41
     Mlle
    1.36
     Docteur
    1.34
     accla
    1.34
     rafra
    1.34
    Activations Density 0.201%

    No Known Activations