© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12947
    Prev
    Next
    INDEX
    Explanations

    details and unfolding events in a narrative, specifically focusing on plot sequences

    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
    204
    +0.16
    0.6%
    506
    +0.15
    0.6%
    553
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.16
    0.02
    506
    +0.15
    0.02
    553
    +0.13
    0.02
    Negative Logits
     koš
    -0.54
     kooper
    -0.51
     Frö
    -0.51
     farba
    -0.50
     gero
    -0.50
    parency
    -0.49
     mena
    -0.49
    dics
    -0.48
     Nö
    -0.48
     konserv
    -0.48
    POSITIVE LOGITS
     plot
    1.36
     plots
    1.25
    plot
    1.23
     Plot
    1.18
     Plots
    1.15
    Plot
    1.11
     PLOT
    1.10
    plots
    1.03
    PLOT
    1.02
     plotting
    1.01
    Activations Density 0.071%

    No Known Activations