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. 1604
    Prev
    Next
    INDEX
    Explanations

    references to social status and hierarchies

    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
    1618
    +0.14
    0.6%
    1306
    +0.14
    0.5%
    1387
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1306
    +0.14
    0.03
    1618
    +0.14
    0.02
    1387
    +0.11
    0.02
    Negative Logits
     naran
    -0.58
     Joaqu
    -0.53
     Punj
    -0.52
     capitan
    -0.51
    cciale
    -0.50
     decret
    -0.50
     schi
    -0.49
    ceptives
    -0.49
     pinak
    -0.49
    icleta
    -0.47
    POSITIVE LOGITS
     status
    1.42
     Status
    1.35
    status
    1.30
     STATUS
    1.25
     statuses
    1.20
    Status
    1.19
     getStatus
    1.15
    STATUS
    1.13
    setStatus
    1.13
    getStatus
    1.11
    Activations Density 0.072%

    No Known Activations