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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13687
    Prev
    Next
    INDEX
    Explanations

    phrases related to team dynamics and organization, with a focus on sports teams

    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
    599
    +0.14
    0.4%
    227
    +0.12
    0.4%
    1870
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    733
    +0.14
    0.09
    227
    +0.12
    0.10
    1870
    +0.11
    0.05
    Negative Logits
    nodoc
    -0.59
    Espèce
    -0.57
    Consejo
    -0.57
    Referencies
    -0.57
    Erreferentziak
    -0.55
    ;%%
    -0.52
    )‏
    -0.52
    '])->
    -0.52
    ുന്ന
    -0.51
    }',
    -0.51
    POSITIVE LOGITS
     shenan
    1.91
     maneu
    1.83
     impra
    1.81
     depic
    1.81
     snoopy
    1.77
     reluct
    1.76
     milf
    1.73
     increa
    1.68
     scrat
    1.67
     excru
    1.67
    Activations Density 1.094%

    No Known Activations