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. 741
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and legislation

    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
    1150
    +0.15
    0.5%
    1741
    +0.14
    0.4%
    2019
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.15
    0.04
    1406
    +0.14
    0.03
    382
    +0.14
    0.04
    Negative Logits
     batte
    -1.26
     sappi
    -1.24
     peculi
    -1.23
     alkoh
    -1.21
     ordina
    -1.19
     abbra
    -1.17
     kosme
    -1.17
     sopr
    -1.17
     immen
    -1.16
     obb
    -1.15
    POSITIVE LOGITS
     there
    0.90
     “
    0.79
     it
    0.77
     "
    0.74
     this
    0.70
     these
    0.70
     «
    0.70
     they
    0.69
     although
    0.67
     devouring
    0.65
    Activations Density 0.161%

    No Known Activations