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

    Neuronpedia

    APICircuit 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. 11722
    Prev
    Next
    INDEX
    Explanations

    terms related to vertebrate and mammalian biology, particularly those concerning development and evolutionary classification

    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
    +0.16
    0.9%
    466
    +0.14
    0.8%
    334
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.16
    0.03
    370
    +0.14
    0.03
    268
    +0.11
    0.03
    Negative Logits
    quired
    -1.59
    ISHED
    -1.52
     pus
    -1.49
    signed
    -1.49
     down
    -1.46
     rect
    -1.44
    WARD
    -1.44
    ABLE
    -1.39
    down
    -1.36
     vote
    -1.35
    POSITIVE LOGITS
    erals
    1.75
    aea
    1.64
     species
    1.63
    optera
    1.61
    osaurs
    1.60
     ancestor
    1.59
    idea
    1.55
    oxin
    1.54
    ukary
    1.54
     ecosystems
    1.53
    Activations Density 0.186%

    No Known Activations