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. 29519
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and events

    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
    111
    +0.30
    1.7%
    491
    +0.15
    0.9%
    71
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.30
    0.28
    4
    +0.15
    0.26
    156
    +0.13
    0.26
    Negative Logits
    zo
    -1.61
     lie
    -1.58
     ?
    -1.58
     depend
    -1.43
     bil
    -1.42
    âĢĤ
    -1.40
     nickname
    -1.36
     depended
    -1.33
     mon
    -1.32
     pseud
    -1.32
    POSITIVE LOGITS
     Jobs
    1.76
    úblic
    1.74
    »¿
    1.66
     shoots
    1.66
    reads
    1.63
    aughs
    1.60
    adeon
    1.52
    etica
    1.50
    releases
    1.44
     Review
    1.39
    Activations Density 3.326%

    No Known Activations