© 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. 5916
    Prev
    Next
    INDEX
    Explanations

    the word "useful" in various contexts

    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
    +0.17
    0.9%
    47
    +0.13
    0.6%
    168
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.17
    0.03
    168
    +0.13
    0.04
    1271
    +0.12
    0.03
    Negative Logits
    <bos>
    -3.12
    /***
    -0.81
    
    -0.81
    ⓧ
    -0.80
    /**
    -0.79
     mount
    -0.65
    },{
    -0.64
    /*
    -0.63
    Более
    -0.63
    })();
    -0.61
    POSITIVE LOGITS
     ankara
    1.47
     milano
    1.46
     maroc
    1.41
     italia
    1.40
     wien
    1.39
     fers
    1.37
     eiffel
    1.36
     ibiza
    1.35
     stockholm
    1.35
     riviera
    1.34
    Activations Density 0.201%

    No Known Activations