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. 538
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to politics and historical events

    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
    604
    +0.13
    0.4%
    1842
    +0.10
    0.3%
    872
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.13
    0.04
    1260
    +0.10
    0.02
    227
    +0.09
    0.07
    Negative Logits
     persil
    -1.08
     affez
    -0.96
     fluo
    -0.93
     loto
    -0.93
     frambo
    -0.93
     rhum
    -0.91
     veau
    -0.90
     Chapitre
    -0.89
     ananas
    -0.88
     milano
    -0.87
    POSITIVE LOGITS
     wasn
    0.84
     seemed
    0.81
     was
    0.80
     resulted
    0.77
     reflects
    0.74
     proves
    0.74
     seems
    0.74
     coincided
    0.74
     necessitated
    0.72
     lasted
    0.71
    Activations Density 0.652%

    No Known Activations