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. 15021
    Prev
    Next
    INDEX
    Explanations

    postal addresses and related information

    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
    241
    +0.17
    0.9%
    1047
    +0.16
    0.8%
    1392
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.17
    0.05
    1741
    +0.16
    -0.00
    227
    +0.13
    0.06
    Negative Logits
     krep
    -0.72
     Italij
    -0.63
     veiks
    -0.63
     jeb
    -0.60
     rū
    -0.60
     papild
    -0.59
     usta
    -0.58
     darbu
    -0.58
     vair
    -0.57
    샷
    -0.57
    POSITIVE LOGITS
     BIBSYS
    0.96
     vœ
    0.85
     Docteur
    0.84
     applau
    0.79
     délib
    0.78
     Sén
    0.78
     destina
    0.77
     Chapitre
    0.77
     Secrétaire
    0.76
     canapé
    0.75
    Activations Density 0.615%

    No Known Activations