Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 16048
    Prev
    Next
    INDEX
    Explanations

    text related to music and cultural evolution

    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
    198
    +0.11
    0.3%
    856
    +0.11
    0.3%
    1385
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.11
    0.06
    1948
    +0.11
    0.04
    756
    +0.09
    0.04
    Negative Logits
     pamph
    -0.69
     practition
    -0.63
     kram
    -0.58
     philanth
    -0.56
     resear
    -0.55
     revan
    -0.54
     volunte
    -0.54
     papar
    -0.54
    Vra
    -0.53
     mikrofon
    -0.53
    POSITIVE LOGITS
     modernity
    0.56
    abancı
    0.55
     occident
    0.50
     الدولى
    0.49
     paesi
    0.49
     zachod
    0.48
     modern
    0.48
    modern
    0.47
     modernization
    0.47
    SpringBootTest
    0.45
    Activations Density 0.570%

    No Known Activations