© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7469
    Prev
    Next
    INDEX
    Explanations

    phrases related to rushing or hurrying

    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
    1272
    +0.16
    0.6%
    555
    +0.13
    0.5%
    204
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1272
    +0.16
    0.03
    204
    +0.13
    0.02
    555
    +0.13
    0.02
    Negative Logits
    OGND
    -0.47
     كومونز
    -0.47
    SourceChecksum
    -0.47
    DeleteMapping
    -0.46
    WindowConstants
    -0.46
     հղումներ
    -0.46
    alignSelf
    -0.45
    glEnd
    -0.45
    المناصب
    -0.45
    dollis
    -0.45
    POSITIVE LOGITS
     rush
    1.25
     Rush
    1.19
    Rush
    1.15
     rushes
    1.10
     RUSH
    1.06
     rushing
    1.02
     rushed
    0.98
    rush
    0.96
     hurrying
    0.86
     affor
    0.79
    Activations Density 0.092%

    No Known Activations