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. 577
    Prev
    Next
    INDEX
    Explanations

    locations and characteristics of a specific physical place or area

    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
    964
    +0.12
    0.3%
    939
    +0.11
    0.3%
    1013
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.12
    0.08
    1438
    +0.11
    0.04
    964
    +0.09
    0.04
    Negative Logits
     Keny
    -1.16
     accla
    -1.12
     Minang
    -1.12
     inev
    -1.11
     Confe
    -1.11
     Varan
    -1.09
     increa
    -1.09
     emphat
    -1.09
     disagre
    -1.06
     reluct
    -1.06
    POSITIVE LOGITS
    ValueGeneration
    0.67
    inhabited
    0.66
     occupied
    0.65
    populated
    0.65
     contains
    0.65
     contain
    0.63
    ValueStyle
    0.61
     propOrder
    0.61
     populated
    0.60
     భూ
    0.60
    Activations Density 0.513%

    No Known Activations