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. 3751
    Prev
    Next
    INDEX
    Explanations

    words related to administrative operations or procedures

    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
    513
    +0.18
    0.8%
    1363
    +0.13
    0.6%
    678
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.18
    0.09
    678
    +0.13
    0.10
    513
    +0.13
    0.06
    Negative Logits
    <bos>
    -2.17
     endeavored
    -0.90
     umożli
    -0.82
     endeavoured
    -0.82
     pediu
    -0.81
     caiu
    -0.79
     realizacji
    -0.79
     encontrou
    -0.77
    /**
    -0.77
     endeavouring
    -0.74
    POSITIVE LOGITS
     migli
    1.47
     ridu
    1.34
     sappi
    1.33
     Febru
    1.29
     circon
    1.28
     sopr
    1.25
     curi
    1.24
     cammin
    1.24
     suon
    1.23
     esplor
    1.23
    Activations Density 0.899%

    No Known Activations