© 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 EvalsExportsinterp-engineNEWAPI 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. 4932
    Prev
    Next
    INDEX
    Explanations

    prepositions or phrases starting with 'of'

    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
    752
    +0.20
    0.6%
    50
    +0.16
    0.5%
    2019
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.20
    0.04
    16
    +0.16
    0.04
    1270
    +0.10
    0.04
    Negative Logits
    <bos>
    -0.84
     sape
    -0.64
    Formazione
    -0.57
     Luglio
    -0.56
    errHandler
    -0.56
    TypedDataSet
    -0.55
     europé
    -0.55
     porsi
    -0.54
     bottes
    -0.54
    rouwen
    -0.53
    POSITIVE LOGITS
     introducing
    0.62
     intersper
    0.56
     neglecting
    0.56
     omitting
    0.55
     installing
    0.54
     having
    0.54
     deploying
    0.53
     using
    0.53
     applying
    0.53
    WRENCE
    0.53
    Activations Density 0.183%

    No Known Activations