© 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. 5927
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-improvement or self-focused activities

    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
    1482
    +0.14
    0.5%
    1256
    +0.10
    0.4%
    892
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1482
    +0.14
    0.04
    892
    +0.10
    0.04
    1124
    +0.10
    0.03
    Negative Logits
     shenan
    -0.59
     mercurial
    -0.58
     reluct
    -0.56
     Machia
    -0.55
     apprehen
    -0.55
    barbie
    -0.53
     broadway
    -0.53
     Aftermath
    -0.52
    rachel
    -0.52
     maneu
    -0.51
    POSITIVE LOGITS
    Self
    1.23
    self
    1.14
     self
    1.14
     Self
    1.13
     SELF
    1.10
    SELF
    1.07
     selves
    0.87
    Selbst
    0.76
     Selbst
    0.67
     burbu
    0.66
    Activations Density 0.070%

    No Known Activations