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. 8123
    Prev
    Next
    INDEX
    Explanations

    references to transportation accidents investigated by the National Transportation Safety Board, including details like probable causes and aircraft information

    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
    +0.30
    1.2%
    1499
    +0.10
    0.4%
    1438
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.30
    0.07
    1499
    +0.10
    0.07
    1815
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.14
     nahilalakip
    -0.67
    public
    -0.62
    sizeCache
    -0.62
    PLICATE
    -0.60
    énario
    -0.60
    /*++
    -0.58
    //
    -0.58
    CreateMap
    -0.57
    HasAnnotation
    -0.56
    POSITIVE LOGITS
     affor
    1.65
     Juf
    1.64
     accla
    1.63
     increa
    1.56
     emphat
    1.48
     Intere
    1.48
     disagre
    1.47
     milf
    1.47
     strick
    1.46
     Augu
    1.46
    Activations Density 0.854%

    No Known Activations