© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2432
    Prev
    Next
    INDEX
    Explanations

    words related to film genres

    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
    1870
    +0.13
    0.4%
    411
    +0.12
    0.4%
    1059
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.13
    0.01
    841
    +0.12
    0.01
    270
    +0.11
    0.02
    Negative Logits
     répon
    -0.81
     soigne
    -0.74
     umbro
    -0.73
     Bâ
    -0.72
     végétal
    -0.71
     estimat
    -0.71
     ridu
    -0.68
     étend
    -0.68
     fup
    -0.68
     éto
    -0.67
    POSITIVE LOGITS
     genre
    1.30
    genre
    1.09
     genres
    1.08
    Genre
    0.93
     Genre
    0.90
    genres
    0.85
    Genres
    0.71
     жан
    0.65
     Genres
    0.62
    ジャンル
    0.61
    Activations Density 0.095%

    No Known Activations