© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2021
    Prev
    Next
    INDEX
    Explanations

    mentions of singing, especially in different contexts such as a man trying to sing despite being off-key or characters engaging in musical activities

    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
    1276
    +0.15
    0.5%
    201
    +0.14
    0.5%
    1416
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.15
    0.03
    201
    +0.14
    0.02
    1416
    +0.13
    0.03
    Negative Logits
     dó
    -0.61
     للاسماء
    -0.60
    marle
    -0.55
     CreateTagHelper
    -0.55
    istán
    -0.55
    )_/¯
    -0.54
     كومونز
    -0.54
    RetentionPolicy
    -0.54
    ScopeManager
    -0.54
    ceis
    -0.53
    POSITIVE LOGITS
     indestru
    1.30
     hairc
    1.25
     intersper
    1.22
     unspeak
    1.21
     impra
    1.21
     Singing
    1.20
     reluct
    1.20
     impractica
    1.20
     shenan
    1.20
     increa
    1.20
    Activations Density 0.090%

    No Known Activations