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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12123
    Prev
    Next
    INDEX
    Explanations

    code structures and behaviors associated with data handling and processing in programming contexts

    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
    17
    +0.39
    2.5%
    240
    +0.11
    0.7%
    127
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.39
    0.06
    127
    +0.11
    0.13
    217
    +0.11
    0.11
    Negative Logits
    ĻĤ
    -2.75
    ²
    -2.28
    ı
    -2.20
    ŀ
    -2.18
    Ļª
    -2.17
    IJ
    -2.16
    ¤
    -2.15
    ¼
    -2.13
    Ļ
    -2.09
    ©
    -2.08
    POSITIVE LOGITS
    pel
    1.38
     expect
    1.35
    frast
    1.28
    orage
    1.27
    orrow
    1.25
     occupancy
    1.25
    uple
    1.23
    culos
    1.22
    urbs
    1.21
    dom
    1.21
    Activations Density 3.834%

    No Known Activations