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. 637
    Prev
    Next
    INDEX
    Explanations

    keywords related to "Pin" and "pointed"

    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
    130
    +0.14
    0.6%
    1194
    +0.13
    0.5%
    757
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.14
    0.03
    1194
    +0.13
    0.02
    757
    +0.13
    0.03
    Negative Logits
     naer
    -0.82
     nuoc
    -0.77
     maksi
    -0.76
     saad
    -0.75
     saar
    -0.74
     roh
    -0.73
     prae
    -0.73
     alpes
    -0.73
     lemp
    -0.71
     territo
    -0.71
    POSITIVE LOGITS
     pin
    1.47
     Pin
    1.43
     pins
    1.33
    Pin
    1.32
    pin
    1.28
     PIN
    1.24
     pinned
    1.16
     pinning
    1.15
     Pins
    1.14
    pins
    1.11
    Activations Density 0.107%

    No Known Activations