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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 173
    Prev
    Next
    INDEX
    Explanations

    financial terms and data points related to economics and business

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1380
    +0.09
    0.4%
    1553
    +0.09
    0.3%
    283
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1380
    +0.09
    0.11
    736
    +0.09
    0.10
    1288
    +0.08
    0.08
    Negative Logits
     do
    -1.44
    ,
    -1.40
     so
    -1.40
     can
    -1.38
     continue
    -1.37
     to
    -1.35
     pass
    -1.32
     in
    -1.32
     as
    -1.31
    .
    -1.31
    POSITIVE LOGITS
     increa
    4.59
     fta
    4.52
     thut
    4.43
     squa
    4.42
     maneu
    4.41
     wien
    4.40
     ?...
    4.38
     emphat
    4.38
     ftu
    4.38
     guarante
    4.36
    Activations Density 1.052%

    No Known Activations