Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8383
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace safety and communication

    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
    2034
    +0.20
    0.7%
    674
    +0.17
    0.5%
    478
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    610
    +0.20
    0.06
    1128
    +0.17
    0.05
    478
    +0.16
    0.04
    Negative Logits
     shenan
    -1.65
     unspeak
    -1.53
     disagre
    -1.49
     maneu
    -1.47
     hairc
    -1.45
     unwarran
    -1.45
     horrend
    -1.42
     apprehen
    -1.40
     affor
    -1.39
     impra
    -1.39
    POSITIVE LOGITS
    <bos>
    1.23
     ***!
    0.82
    ↵↵
    0.81
    ']."
    0.78
    ↵↵↵
    0.77
    <eos>
    0.77
    __))
    0.76
    ferrer
    0.75
    }}
    0.74
    .”
    0.74
    Activations Density 0.151%

    No Known Activations