© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    positive descriptive words

    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
    410
    +0.11
    0.4%
    596
    +0.11
    0.4%
    605
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.11
    0.05
    410
    +0.11
    0.04
    650
    +0.11
    0.04
    Negative Logits
     resultList
    -0.52
    Extrait
    -0.48
    suddenly
    -0.46
    oarece
    -0.45
    Embeddable
    -0.44
     Simultaneously
    -0.44
     plenti
    -0.43
     memberId
    -0.43
     rowCount
    -0.43
     pstmt
    -0.43
    POSITIVE LOGITS
    good
    1.05
     good
    0.99
     GOOD
    0.99
    GOOD
    0.95
    Good
    0.91
     Good
    0.91
    goods
    0.71
     buoni
    0.68
     GOODS
    0.66
     buenas
    0.65
    Activations Density 0.139%

    No Known Activations