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. 8109
    Prev
    Next
    INDEX
    Explanations

    phrases related to exceeding limits, particularly in the context of influence, control, or promises

    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
    +0.13
    0.6%
    662
    +0.10
    0.4%
    1334
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.13
    0.05
    1334
    +0.10
    0.04
    1034
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.75
    ⓧ
    -0.65
    },[])
    -0.64
    ButtonModule
    -0.63
    ///**
    -0.63
     join
    -0.63
    ValueGenerated
    -0.62
    /***
    
    -0.61
     Administrativna
    -0.61
    Πε
    -0.60
    POSITIVE LOGITS
     jaya
    1.49
     bandung
    1.42
     Minang
    1.41
     practition
    1.39
     sovere
    1.33
     overla
    1.32
     stockholm
    1.31
     maroc
    1.31
     levis
    1.30
     Confe
    1.30
    Activations Density 0.217%

    No Known Activations