© 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. 10944
    Prev
    Next
    INDEX
    Explanations

    locations or descriptions related to interior spaces

    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
    897
    +0.16
    0.6%
    680
    +0.13
    0.5%
    878
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.16
    0.02
    1352
    +0.13
    0.02
    765
    +0.13
    0.02
    Negative Logits
     accla
    -1.00
     unwarran
    -0.93
     suscep
    -0.91
     philanth
    -0.90
     indestru
    -0.89
     encomp
    -0.89
     disagre
    -0.87
     unlaw
    -0.85
     emphat
    -0.84
     unve
    -0.82
    POSITIVE LOGITS
     interior
    1.21
     Interior
    1.16
    Interior
    1.10
    interior
    1.01
     interiors
    0.96
     INTERIOR
    0.87
    INTERIOR
    0.77
     interiores
    0.74
    nterior
    0.71
     exterior
    0.69
    Activations Density 0.058%

    No Known Activations