© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2440
    Prev
    Next
    INDEX
    Explanations

    instances of similes, comparisons, and descriptive language

    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
    1343
    +0.09
    0.3%
    289
    +0.09
    0.3%
    1984
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.09
    0.05
    2047
    +0.09
    0.04
    16
    +0.08
    0.06
    Negative Logits
     snoopy
    -0.93
     pegasus
    -0.91
     strick
    -0.91
     parch
    -0.89
     celtic
    -0.88
     jurassic
    -0.86
     scottish
    -0.85
     outlander
    -0.85
     milf
    -0.83
     beatles
    -0.82
    POSITIVE LOGITS
    Več
    0.81
    Glej
    0.78
    Conheça
    0.77
    Če
    0.73
    Bereits
    0.69
    Spesifikasi
    0.67
    Specifik
    0.66
    Sklici
    0.66
    Trotz
    0.65
    Acab
    0.64
    Activations Density 0.389%

    No Known Activations