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. 719
    Prev
    Next
    INDEX
    Explanations

    organizations, event names, and contacts in text

    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
    517
    +0.15
    0.8%
    1971
    +0.13
    0.7%
    667
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1971
    +0.15
    0.07
    1343
    +0.13
    0.10
    683
    +0.12
    0.08
    Negative Logits
    <bos>
    -1.88
     intersper
    -1.16
    /**
    -0.87
    
    
    -0.85
     endow
    -0.83
     impelled
    -0.82
    <?
    -0.81
     overcrow
    -0.81
     underval
    -0.80
     disbur
    -0.78
    POSITIVE LOGITS
     cioc
    0.67
    Sklici
    0.65
    ihnachts
    0.64
     zub
    0.63
    erenc
    0.63
     tristes
    0.62
     Politica
    0.61
    ihnachten
    0.60
    zsef
    0.60
    acheco
    0.59
    Activations Density 1.109%

    No Known Activations