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. 3040
    Prev
    Next
    INDEX
    Explanations

    information about music production and songwriting techniques

    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
    872
    +0.14
    0.4%
    2047
    +0.10
    0.3%
    1150
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.14
    0.06
    2047
    +0.10
    0.03
    1317
    +0.10
    0.04
    Negative Logits
     Juf
    -1.58
     squa
    -1.56
     Intere
    -1.54
     Keny
    -1.47
     oleo
    -1.43
     Khart
    -1.43
     Augu
    -1.42
     stockholm
    -1.41
     unden
    -1.41
     fta
    -1.41
    POSITIVE LOGITS
     ideas
    0.84
     inspiration
    0.68
     idea
    0.66
     Ideas
    0.65
     outline
    0.65
    <bos>
    0.64
     draft
    0.64
     write
    0.64
     creative
    0.64
     sketch
    0.63
    Activations Density 0.471%

    No Known Activations