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. 1461
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and emotions

    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
    1445
    +0.11
    0.3%
    1381
    +0.10
    0.3%
    2034
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.11
    0.05
    1445
    +0.10
    0.06
    1592
    +0.09
    0.03
    Negative Logits
     Settembre
    -1.06
     Ottobre
    -1.03
     Février
    -1.02
     Giugno
    -1.02
     Luglio
    -0.99
     sappi
    -0.98
     fua
    -0.92
     quæ
    -0.92
     vorrei
    -0.92
     cæ
    -0.91
    POSITIVE LOGITS
     doing
    0.97
     trying
    0.95
     making
    0.95
     getting
    0.90
     giving
    0.87
     preparing
    0.86
     looking
    0.85
     creating
    0.85
     putting
    0.85
     providing
    0.84
    Activations Density 0.453%

    No Known Activations