© 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. 2538
    Prev
    Next
    INDEX
    Explanations

    advice and tips related to pursuing a creative career, specifically in fields like writing, game design, or music production

    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
    381
    +0.10
    0.3%
    50
    +0.10
    0.3%
    1510
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.10
    0.03
    288
    +0.10
    0.04
    658
    +0.07
    0.05
    Negative Logits
     Juf
    -2.03
     fta
    -2.02
     secon
    -2.00
     effe
    -1.99
     inev
    -1.97
     squa
    -1.97
     dises
    -1.94
     increa
    -1.92
     wherea
    -1.87
     nece
    -1.86
    POSITIVE LOGITS
     always
    0.82
     keep
    0.82
     focus
    0.78
     never
    0.78
     avoid
    0.77
     stay
    0.76
     don
    0.74
     respect
    0.73
     patience
    0.72
     listen
    0.70
    Activations Density 0.461%

    No Known Activations