Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 780
    Prev
    Next
    INDEX
    Explanations

    elements related to Haskell programming language syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    68
    +0.17
    1.0%
    1068
    +0.17
    0.9%
    1035
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.05
    1741
    +0.17
    0.01
    1097
    +0.17
    0.04
    Negative Logits
    <bos>
    -0.76
     alko
    -0.68
     kasa
    -0.62
     lü
    -0.62
     kapital
    -0.60
     antik
    -0.60
     torner
    -0.58
     alkoh
    -0.58
     Bekasi
    -0.58
     konkre
    -0.58
    POSITIVE LOGITS
    Havolalar
    0.66
     Haskell
    0.64
     hornblende
    0.64
     hydrocarbons
    0.64
     brilla
    0.63
    askell
    0.62
     psycopg
    0.62
     ::
    0.61
    mistak
    0.60
     joaat
    0.59
    Activations Density 0.341%

    No Known Activations