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. 14981
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious or mystical concepts and places

    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
    752
    +0.16
    0.6%
    1264
    +0.15
    0.6%
    75
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.12
    1614
    +0.15
    0.10
    1043
    +0.11
    0.09
    Negative Logits
    /**
    -0.93
     held
    -0.80
    
    
    -0.80
    /*
    -0.79
    ,
    -0.77
     too
    -0.76
     التهاب
    -0.75
     on
    -0.75
     and
    -0.75
     won
    -0.75
    POSITIVE LOGITS
     maneu
    1.90
     squa
    1.88
     eyel
    1.87
     erad
    1.86
     suscep
    1.83
     fortn
    1.79
     scrat
    1.75
     excru
    1.74
     véhic
    1.74
    fordable
    1.74
    Activations Density 0.889%

    No Known Activations