© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5866
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports teams and players

    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
    +0.19
    0.9%
    1334
    +0.11
    0.5%
    645
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.19
    0.08
    1415
    +0.11
    0.05
    122
    +0.09
    0.06
    Negative Logits
    <bos>
    -1.52
     intersper
    -1.37
     endow
    -0.85
     gratify
    -0.84
    /***
    -0.83
     ascribe
    -0.80
     rouse
    -0.78
     banish
    -0.77
     harmonize
    -0.77
     acquaint
    -0.76
    POSITIVE LOGITS
     venuto
    0.98
     dimentic
    0.76
     rechange
    0.75
     riuscito
    0.72
     rimasto
    0.72
     sentito
    0.70
     potuto
    0.69
     pymongo
    0.68
     chrysler
    0.68
     innamor
    0.68
    Activations Density 0.562%

    No Known Activations