© 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. 4040
    Prev
    Next
    INDEX
    Explanations

    words related to movies and filmmaking

    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
    2019
    +0.16
    0.5%
    382
    +0.16
    0.5%
    1741
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.16
    0.13
    1265
    +0.16
    0.09
    736
    +0.13
    0.10
    Negative Logits
     sfera
    -1.15
     cioc
    -1.13
     parati
    -1.09
     lampa
    -1.05
     fono
    -1.03
     tuta
    -1.03
     toscana
    -1.03
     maroc
    -1.03
     artig
    -1.01
     maniere
    -1.01
    POSITIVE LOGITS
     endeavouring
    0.88
     but
    0.85
     unspeak
    0.85
     subver
    0.79
     disregarding
    0.76
     depriving
    0.76
     endeav
    0.74
     vainly
    0.73
     affording
    0.73
     ineffec
    0.73
    Activations Density 0.748%

    No Known Activations