© 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. 11574
    Prev
    Next
    INDEX
    Explanations

    expressions related to disappointment or frustration

    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
    604
    +0.09
    0.3%
    1379
    +0.09
    0.3%
    1964
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    584
    +0.09
    0.04
    1056
    +0.09
    0.05
    416
    +0.09
    0.04
    Negative Logits
     idr
    -0.80
     maske
    -0.80
    <bos>
    -0.79
     pymysql
    -0.75
     boks
    -0.75
     heapq
    -0.75
     myn
    -0.75
     gmbh
    -0.74
     vnd
    -0.72
    :,,
    -0.70
    POSITIVE LOGITS
     how
    0.63
     lack
    0.59
     being
    0.53
     what
    0.52
     having
    0.50
     inability
    0.49
     hearing
    0.48
     finding
    0.47
     prospect
    0.46
     his
    0.45
    Activations Density 0.244%

    No Known Activations