© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14445
    Prev
    Next
    INDEX
    Explanations

    questions related to taking action and making a difference in the world

    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
    1786
    +0.08
    0.2%
    592
    +0.08
    0.2%
    1629
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    592
    +0.08
    0.02
    1786
    +0.08
    0.01
    1395
    +0.08
    0.04
    Negative Logits
     fta
    -1.43
     reluct
    -1.33
     increa
    -1.29
     ftu
    -1.28
     strick
    -1.27
     thut
    -1.27
     depic
    -1.27
     fup
    -1.25
     encomp
    -1.24
     seiz
    -1.23
    POSITIVE LOGITS
     contribution
    0.74
     contribute
    0.71
     contributions
    0.67
     contributing
    0.65
     impact
    0.64
     action
    0.63
     volunteer
    0.60
     activism
    0.59
     contributes
    0.58
     individual
    0.57
    Activations Density 0.653%

    No Known Activations