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. 28804
    Prev
    Next
    INDEX
    Explanations

    technical terms and configurations related to system processes and software

    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
    +0.14
    0.8%
    5
    +0.14
    0.8%
    98
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.14
    0.11
    292
    +0.14
    0.13
    118
    +0.12
    0.17
    Negative Logits
     fines
    -1.52
    §
    -1.49
     weights
    -1.45
     verd
    -1.39
    outs
    -1.37
     notices
    -1.37
    missive
    -1.35
    nement
    -1.33
     sage
    -1.32
     presentation
    -1.30
    POSITIVE LOGITS
    wordpress
    1.58
    ife
    1.58
    affe
    1.55
    inary
    1.50
     Firstly
    1.49
    obal
    1.42
    enez
    1.39
    ait
    1.39
    googleapis
    1.37
    ]$
    1.35
    Activations Density 4.396%

    No Known Activations