© 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. 13736
    Prev
    Next
    INDEX
    Explanations

    mentions of "loss" of various kinds

    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
    303
    +0.14
    0.5%
    130
    +0.13
    0.5%
    662
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.14
    0.04
    966
    +0.13
    0.04
    303
    +0.11
    0.04
    Negative Logits
    />";
    -0.46
     ""}
    -0.46
    olverine
    -0.44
    ecuted
    -0.41
     possano
    -0.41
     Vere
    -0.41
    commodations
    -0.40
     vere
    -0.40
    pectives
    -0.39
     esistono
    -0.38
    POSITIVE LOGITS
    Loss
    1.16
    loss
    1.15
     Loss
    1.15
     loss
    1.13
     Losses
    1.09
     LOSS
    1.06
     losses
    1.04
    Losses
    1.00
     lost
    0.95
     LOST
    0.95
    Activations Density 0.089%

    No Known Activations