© 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. 7268
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports teams and team managers

    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
    1334
    +0.18
    0.8%
    757
    +0.17
    0.7%
    889
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.18
    0.07
    678
    +0.17
    0.06
    1177
    +0.14
    0.03
    Negative Logits
     unspeak
    -1.22
     implacable
    -1.05
     barbarous
    -1.01
     vainly
    -1.01
     impelled
    -1.01
     insensible
    -1.00
     ardour
    -1.00
     disreg
    -0.99
     indescri
    -0.98
     liberality
    -0.97
    POSITIVE LOGITS
     migli
    1.33
     alkoh
    1.10
     kosme
    1.09
     apparti
    1.09
     kompati
    1.07
     utop
    1.04
     minimalis
    1.04
     kritis
    1.03
     praktik
    1.03
     silikon
    1.02
    Activations Density 0.338%

    No Known Activations