© 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. 14699
    Prev
    Next
    INDEX
    Explanations

    phrases related to career development

    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
    198
    +0.09
    0.3%
    405
    +0.09
    0.3%
    674
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.09
    0.04
    405
    +0.09
    0.03
    2045
    +0.09
    0.04
    Negative Logits
    FontOfSize
    -0.50
     instead
    -0.45
     was
    -0.45
     became
    -0.44
    suddenly
    -0.43
     anyone
    -0.43
    KEYCODE
    -0.42
     wasn
    -0.42
    InputTagHelper
    -0.41
     Anyone
    -0.41
    POSITIVE LOGITS
    <bos>
    1.14
     nutella
    0.98
     doman
    0.97
     affez
    0.95
     milano
    0.95
     sappi
    0.94
     soggior
    0.94
     territo
    0.89
     napoli
    0.89
     ristor
    0.86
    Activations Density 0.119%

    No Known Activations