© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5848
    Prev
    Next
    INDEX
    Explanations

    fantasy football-related terms and 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
    1253
    +0.15
    0.4%
    736
    +0.10
    0.3%
    1284
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.04
    1555
    +0.10
    0.04
    581
    +0.09
    0.03
    Negative Logits
     affari
    -0.68
     accordo
    -0.66
     paradiso
    -0.66
     Mémoires
    -0.65
     cammino
    -0.65
     onore
    -0.63
     affitto
    -0.63
     antichi
    -0.63
     noss
    -0.62
     eccell
    -0.62
    POSITIVE LOGITS
     minimalis
    0.63
     underrated
    0.56
     overrated
    0.53
     ficando
    0.53
     potensi
    0.52
     picks
    0.51
     nakalista
    0.51
    quehanna
    0.50
    Continu
    0.50
     praktik
    0.50
    Activations Density 0.357%

    No Known Activations