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. 8918
    Prev
    Next
    INDEX
    Explanations

    mentions of when articles or posts were published

    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
    11
    +0.14
    0.7%
    1053
    +0.14
    0.7%
    172
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.04
    1343
    +0.14
    0.06
    690
    +0.14
    0.03
    Negative Logits
     quitted
    -1.12
     disagre
    -1.06
     apprehen
    -1.03
     McLaugh
    -0.94
     impelled
    -0.93
     depic
    -0.93
     gaily
    -0.89
     intersper
    -0.88
     effectually
    -0.88
     reluct
    -0.86
    POSITIVE LOGITS
     Expedia
    0.75
     spedizione
    0.65
     accomplished
    0.63
    calaure
    0.63
    complished
    0.62
     Ehre
    0.62
     emp
    0.61
    complish
    0.59
     accomplishment
    0.58
     hini
    0.58
    Activations Density 0.495%

    No Known Activations