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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8266
    Prev
    Next
    INDEX
    Explanations

    mentions of resources or the need for resources in contexts such as technology, healthcare/counseling, and economic/political situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.14
    0.5%
    1763
    +0.12
    0.4%
    1472
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.14
    0.02
    1140
    +0.12
    0.02
    1763
    +0.11
    0.02
    Negative Logits
     aboli
    -0.57
    SneakyThrows
    -0.55
     felipe
    -0.54
     salvare
    -0.53
     comis
    -0.51
     Siria
    -0.51
     SUDOC
    -0.51
     Valentín
    -0.51
     josé
    -0.50
     invita
    -0.50
    POSITIVE LOGITS
     resources
    1.42
     resource
    1.38
     Resources
    1.30
     Resource
    1.23
    resources
    1.22
     RESOURCES
    1.21
     RESOURCE
    1.20
    resource
    1.19
    Resources
    1.16
    Resource
    1.12
    Activations Density 0.074%

    No Known Activations