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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2728
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions or events

    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
    674
    +0.24
    0.7%
    1843
    +0.09
    0.3%
    1253
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1826
    +0.24
    0.00
    1477
    +0.09
    0.05
    343
    +0.08
    0.04
    Negative Logits
    TagMode
    -0.72
    UnusedPrivate
    -0.70
    AlterField
    -0.67
    EndTag
    -0.67
     <<<<<<<<<<<<<<
    -0.63
    Demografie
    -0.63
    MatButtonModule
    -0.63
    GeoNames
    -0.61
    Palmar
    -0.61
    gridx
    -0.60
    POSITIVE LOGITS
     affor
    1.76
     increa
    1.68
     guarante
    1.68
     intersper
    1.67
     unden
    1.64
     volunte
    1.63
     desir
    1.62
     scrat
    1.62
     michelin
    1.61
     lola
    1.61
    Activations Density 0.443%

    No Known Activations