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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5381
    Prev
    Next
    INDEX
    Explanations

    references to equity and securities in the finance industry

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    161
    +0.18
    0.9%
    156
    +0.15
    0.7%
    501
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.18
    0.03
    1870
    +0.15
    0.02
    501
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.29
     superintend
    -0.71
     defray
    -0.71
     shewn
    -0.70
     endeavouring
    -0.68
     unlaw
    -0.68
     Shakspeare
    -0.67
     gratify
    -0.66
     Whence
    -0.66
     intersper
    -0.64
    POSITIVE LOGITS
     equity
    1.43
     Equity
    1.40
    equity
    1.35
    Equity
    1.31
     equities
    0.98
     EQU
    0.95
     Equ
    0.91
     tanong
    0.87
     paradiso
    0.81
    eq
    0.81
    Activations Density 0.447%

    No Known Activations