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. 2987
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of educational institutions

    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
    227
    +0.19
    0.6%
    752
    +0.12
    0.4%
    1343
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.19
    0.05
    1410
    +0.12
    0.04
    1336
    +0.12
    0.04
    Negative Logits
     blackish
    -0.91
     purplish
    -0.89
     overcrow
    -0.86
     friable
    -0.83
     lmfao
    -0.82
     disreg
    -0.81
     greyish
    -0.80
     moistened
    -0.77
     purée
    -0.76
     sessile
    -0.75
    POSITIVE LOGITS
     simplif
    1.17
     déclen
    1.09
     rafra
    1.06
     surpl
    1.06
     redé
    1.06
     renou
    1.03
     Chá
    1.03
     Keny
    1.01
     verrou
    1.00
     obé
    1.00
    Activations Density 0.167%

    No Known Activations