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. 10-RES-JB
    6. 6896
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and geographical locations related to cultural and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    783
    +0.13
    0.6%
    50
    +0.12
    0.5%
    629
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.08
    1343
    +0.12
    0.07
    304
    +0.10
    0.00
    Negative Logits
    <bos>
    -2.35
     Ottobre
    -1.10
    Allora
    -1.00
     Settembre
    -0.99
    Tutto
    -0.90
     Giugno
    -0.86
     popoli
    -0.84
    Quali
    -0.84
    Ottimo
    -0.81
    Molto
    -0.81
    POSITIVE LOGITS
     ftu
    2.77
     fta
    2.68
     aen
    2.65
     thut
    2.55
     fto
    2.55
     vns
    2.44
     ftre
    2.41
     fup
    2.40
     tew
    2.39
     effe
    2.37
    Activations Density 0.384%

    No Known Activations