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. 6147
    Prev
    Next
    INDEX
    Explanations

    the word "rather" followed by either a verb or a negation

    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
    161
    +0.13
    0.4%
    50
    +0.13
    0.4%
    1065
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1839
    +0.13
    0.03
    426
    +0.13
    0.02
    989
    +0.11
    0.02
    Negative Logits
    echo
    -0.58
    Excluir
    -0.58
    isset
    -0.56
    AfterViewInit
    -0.56
    DecimalFormat
    -0.55
    extend
    -0.54
    foreach
    -0.54
    美
    -0.53
    catch
    -0.53
    tick
    -0.52
    POSITIVE LOGITS
     swarovski
    1.52
     depic
    1.34
     eiffel
    1.30
     stockholm
    1.29
     eyel
    1.28
     flyknit
    1.28
     lola
    1.25
     ecru
    1.24
     hairc
    1.23
     tiffany
    1.23
    Activations Density 0.195%

    No Known Activations