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. 729
    Prev
    Next
    INDEX
    Explanations

    places and entities related to schools, universities, events, and locations

    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
    1013
    +0.16
    0.5%
    227
    +0.15
    0.5%
    690
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.07
    964
    +0.15
    0.06
    1013
    +0.14
    0.06
    Negative Logits
     imparare
    -0.94
     vogli
    -0.90
     comprendere
    -0.87
     dicono
    -0.85
     abbiano
    -0.84
     vogliono
    -0.82
     affez
    -0.82
    tldr
    -0.77
     rispond
    -0.77
     ricordare
    -0.76
    POSITIVE LOGITS
     vecteur
    0.73
     noyau
    0.65
     levier
    0.65
     plongée
    0.64
     vettore
    0.64
     mécanisme
    0.62
     alip
    0.60
    CPtr
    0.60
     oeil
    0.59
     laço
    0.59
    Activations Density 0.277%

    No Known Activations