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. 14681
    Prev
    Next
    INDEX
    Explanations

    information related to sales figures and company expansions

    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
    +0.18
    0.7%
    1527
    +0.09
    0.4%
    404
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.18
    0.06
    776
    +0.09
    0.07
    1081
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.34
    Skocz
    -0.71
    lateinit
    -0.67
    /*---
    -0.67
    IActionResult
    -0.66
    ništvo
    -0.66
    queryInterface
    -0.66
    GIH
    -0.65
    SharedDtor
    -0.65
    ksikon
    -0.65
    POSITIVE LOGITS
     disagre
    2.09
     increa
    1.99
     impra
    1.98
     maneu
    1.94
     stockholm
    1.93
     reluct
    1.93
     affor
    1.92
     inev
    1.89
     thut
    1.88
     fta
    1.84
    Activations Density 0.848%

    No Known Activations