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. 1164
    Prev
    Next
    INDEX
    Explanations

    words related to specific ethnic or cultural identities, particularly Jewish cultural terms

    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
    50
    +0.21
    1.0%
    1145
    +0.15
    0.7%
    394
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.21
    0.11
    1987
    +0.15
    0.08
    1097
    +0.12
    0.09
    Negative Logits
    <bos>
    -2.64
     gynnwys
    -0.76
    displayquote
    -0.71
    SourceChecksum
    -0.69
     الحره
    -0.69
    MemoryWarning
    -0.68
     насеља
    -0.67
    Související
    -0.65
     AssemblyCompany
    -0.65
     autorytatywna
    -0.64
    POSITIVE LOGITS
     thut
    1.41
     ftu
    1.32
     reft
    1.29
     ftre
    1.28
     Confu
    1.28
     fta
    1.26
     fup
    1.24
     Augu
    1.22
     foon
    1.20
     beft
    1.19
    Activations Density 0.685%

    No Known Activations