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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29043
    Prev
    Next
    INDEX
    Explanations

    terms related to epithelial characteristics and differentiation in cellular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.19
    1.1%
    487
    +0.12
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.19
    0.01
    289
    +0.12
    0.01
    345
    +0.12
    0.01
    Negative Logits
     teach
    -1.65
     exact
    -1.55
     gradual
    -1.52
     done
    -1.50
     practice
    -1.48
     teachers
    -1.47
     concise
    -1.45
    jour
    -1.44
     practical
    -1.43
     general
    -1.42
    POSITIVE LOGITS
    ·¸
    4.28
    ł
    4.28
    ¢
    4.22
    ij
    4.18
    ĭ
    4.14
    Ģ
    4.09
    į
    4.06
    ¦
    4.06
    Ĩ
    4.01
    Ĵ
    4.01
    Activations Density 0.047%

    No Known Activations