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. 95
    Prev
    Next
    INDEX
    Explanations

    texts discussing news, articles, and comments sections on various topics

    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
    +0.21
    0.7%
    1150
    +0.09
    0.3%
    1008
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1685
    +0.21
    0.05
    1973
    +0.09
    0.05
    106
    +0.07
    0.05
    Negative Logits
    <bos>
    -1.78
    /***
    
    -0.69
    HasColumnType
    -0.62
    HasIndex
    -0.61
     onBind
    -0.59
    loài
    -0.58
     pudesse
    -0.57
    setViewName
    -0.56
    Vegeu
    -0.56
    Открыть
    -0.56
    POSITIVE LOGITS
     maneu
    1.64
     affor
    1.63
     disagre
    1.58
     increa
    1.52
     impra
    1.47
     accla
    1.46
     withal
    1.44
     unspeak
    1.42
     bandung
    1.40
     jaya
    1.38
    Activations Density 0.282%

    No Known Activations