© 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. 6-RES-JB
    11. 5081
    Prev
    Next
    INDEX
    Explanations

    information about gasoline prices, specifically changes in prices over time

    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
    50
    +0.18
    0.7%
    1385
    +0.10
    0.4%
    1233
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1267
    +0.18
    0.05
    1385
    +0.10
    0.04
    164
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.16
     encomp
    -0.94
     intersper
    -0.94
    /***
    -0.90
     vainly
    -0.89
     defray
    -0.86
     disbur
    -0.86
     reconno
    -0.84
     quitted
    -0.84
     adjour
    -0.81
    POSITIVE LOGITS
     gasoline
    0.87
     petrol
    0.82
     benzina
    0.79
     barbacoa
    0.73
    capulco
    0.72
     fuel
    0.71
     tortas
    0.70
     churrasco
    0.69
     gasolina
    0.69
    roleum
    0.69
    Activations Density 0.170%

    No Known Activations