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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4590
    Prev
    Next
    INDEX
    Explanations

    descriptions related to travel accommodations and tourist attractions

    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
    82
    +0.19
    1.0%
    1983
    +0.17
    0.9%
    699
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.19
    0.03
    1983
    +0.17
    0.03
    699
    +0.15
    0.03
    Negative Logits
    <bos>
    -1.07
    rrggbb
    -0.69
     مرئيه
    -0.63
     εφ
    -0.57
     nahilalakip
    -0.57
    
    -0.54
     Gerard
    -0.53
    Aholisi
    -0.52
    SourceChecksum
    -0.52
    MessageTagHelper
    -0.51
    POSITIVE LOGITS
     ··
    1.00
     ·
    0.99
     jaya
    0.97
    !!</
    0.97
     unlaw
    0.96
     🥲
    0.94
     catég
    0.93
     maneu
    0.92
     disreg
    0.90
    !!:
    0.90
    Activations Density 0.438%

    No Known Activations