© 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. 13832
    Prev
    Next
    INDEX
    Explanations

    words related to setting limits and testing boundaries in a parenting context

    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
    1077
    +0.10
    0.3%
    866
    +0.09
    0.3%
    78
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1077
    +0.10
    0.04
    866
    +0.09
    0.03
    555
    +0.09
    0.02
    Negative Logits
     Brag
    -0.50
     erad
    -0.49
     implor
    -0.47
     Maw
    -0.46
    brig
    -0.46
     Kuh
    -0.46
     excu
    -0.46
     Davi
    -0.44
     pamph
    -0.44
     OGS
    -0.44
    POSITIVE LOGITS
     testing
    0.94
     Testing
    0.90
     TESTING
    0.89
    Testing
    0.86
     tested
    0.85
     tests
    0.82
    testing
    0.81
     TESTS
    0.81
     test
    0.80
     testers
    0.80
    Activations Density 0.137%

    No Known Activations