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. 1368
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of roles and responsibilities within a social or organizational context

    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
    +0.15
    0.5%
    68
    +0.14
    0.5%
    1527
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1618
    +0.15
    0.04
    68
    +0.14
    0.03
    990
    +0.13
    0.03
    Negative Logits
     carrefour
    -0.60
    ratulations
    -0.60
     trône
    -0.58
     triomphe
    -0.58
     vincere
    -0.56
     fontaine
    -0.56
     Sén
    -0.54
     désert
    -0.53
    tificial
    -0.52
     charité
    -0.52
    POSITIVE LOGITS
     role
    1.36
    role
    1.25
     Role
    1.25
     roles
    1.19
    Role
    1.14
     ROLE
    1.12
     Roles
    1.10
    roles
    1.07
    ROLE
    1.06
     rôle
    0.97
    Activations Density 0.065%

    No Known Activations