© 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. 14177
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing positivity and satisfaction

    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
    25
    +0.15
    0.5%
    1335
    +0.11
    0.4%
    1438
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.15
    0.05
    1335
    +0.11
    0.04
    136
    +0.11
    0.03
    Negative Logits
     abstrait
    -0.74
     bénéfice
    -0.71
    Ehh
    -0.67
     disreg
    -0.66
     coloré
    -0.65
    Mhm
    -0.63
    Cringe
    -0.63
     élar
    -0.63
    Noice
    -0.63
    Hahahahaha
    -0.62
    POSITIVE LOGITS
     everything
    1.08
    everything
    1.04
     Everything
    1.04
    Everything
    1.01
     EVERYTHING
    0.93
     else
    0.74
    THING
    0.73
    itespace
    0.64
    MessageOf
    0.64
     thing
    0.63
    Activations Density 0.098%

    No Known Activations