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. 14888
    Prev
    Next
    INDEX
    Explanations

    phrases related to accidents or incidents involving vehicles

    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
    +0.20
    1.1%
    757
    +0.12
    0.7%
    1678
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.20
    0.04
    1983
    +0.12
    0.03
    897
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.10
    /**
    -0.74
    public
    -0.74
     get
    -0.73
      
    -0.72
    val
    -0.72
    vec
    -0.72
     implement
    -0.71
     continue
    -0.70
     promote
    -0.70
    POSITIVE LOGITS
     swarovski
    1.69
     cabrio
    1.65
     ecru
    1.64
     affez
    1.63
     maroc
    1.62
     jaya
    1.60
     lele
    1.60
     stockholm
    1.59
     wien
    1.59
     tramont
    1.59
    Activations Density 0.096%

    No Known Activations