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

    Neuronpedia

    Jacobian LensNEW
    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. 6177
    Prev
    Next
    INDEX
    Explanations

    text related to personal well-being and lifestyle choices, specifically focusing on the positive impacts of a particular decision or behavior

    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
    453
    +0.13
    0.4%
    599
    +0.12
    0.4%
    1577
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.13
    0.03
    583
    +0.12
    0.02
    510
    +0.11
    0.03
    Negative Logits
     indestru
    -1.58
     shenan
    -1.57
     intersper
    -1.54
     disagre
    -1.53
     reluct
    -1.53
     unspeak
    -1.48
     milf
    -1.47
     inconce
    -1.45
     maneu
    -1.45
     apprehen
    -1.42
    POSITIVE LOGITS
     '\\;'
    0.73
    ContentAlignment
    0.71
     BoxFit
    0.71
    󠁢
    0.68
    AndEndTag
    0.67
    bcryptjs
    0.60
    ValueStyle
    0.59
    AxisAlignment
    0.57
     Himo
    0.55
    andExpect
    0.55
    Activations Density 0.138%

    No Known Activations