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. 14907
    Prev
    Next
    INDEX
    Explanations

    examples related to finance, trading, and strategies

    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
    2034
    +0.19
    0.6%
    382
    +0.16
    0.5%
    1535
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.19
    0.09
    1154
    +0.16
    0.06
    310
    +0.15
    0.04
    Negative Logits
     emphat
    -1.67
     increa
    -1.64
     impra
    -1.62
     reluct
    -1.60
     maneu
    -1.59
     effe
    -1.56
     inev
    -1.56
     disagre
    -1.54
     fuf
    -1.51
     suspic
    -1.50
    POSITIVE LOGITS
     Nor
    0.96
     Instead
    0.93
     sondern
    0.92
     They
    0.91
     nor
    0.88
     ***!
    0.86
     It
    0.83
    <bos>
    0.82
     Rather
    0.80
     But
    0.79
    Activations Density 0.302%

    No Known Activations