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. 15219
    Prev
    Next
    INDEX
    Explanations

    references to custom specifications or creations

    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
    1870
    +0.14
    0.5%
    678
    +0.14
    0.5%
    605
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.03
    1425
    +0.14
    0.02
    1557
    +0.13
    0.02
    Negative Logits
     increa
    -0.84
     perfet
    -0.83
     tolerably
    -0.83
     michelin
    -0.83
     quitted
    -0.81
     scottish
    -0.79
     shewn
    -0.78
     scrat
    -0.78
     guarante
    -0.76
     disagre
    -0.76
    POSITIVE LOGITS
     custom
    1.33
     Custom
    1.31
    custom
    1.30
    Custom
    1.27
    CUSTOM
    1.15
     CUSTOM
    1.12
     customs
    1.07
    setCustom
    0.98
     customize
    0.94
     Customs
    0.94
    Activations Density 0.080%

    No Known Activations