© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14472
    Prev
    Next
    INDEX
    Explanations

    mentions of punishment or wrongdoing

    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
    752
    +0.13
    0.4%
    757
    +0.12
    0.4%
    893
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.13
    0.05
    1602
    +0.12
    0.04
    1328
    +0.10
    0.04
    Negative Logits
     apprehen
    -1.01
     gaily
    -1.00
     shewn
    -0.97
     withal
    -0.94
     feen
    -0.90
     reluct
    -0.87
     gild
    -0.86
     increa
    -0.85
     quitted
    -0.85
     tolerably
    -0.84
    POSITIVE LOGITS
     having
    0.53
     FOR
    0.51
    Fornecedor
    0.51
     for
    0.50
    FOR
    0.50
    for
    0.49
     allegedly
    0.48
     doing
    0.48
     being
    0.47
     guma
    0.47
    Activations Density 0.173%

    No Known Activations