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. 11443
    Prev
    Next
    INDEX
    Explanations

    instances of specific variable assignments or references in programming code

    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
    369
    +0.19
    1.1%
    156
    +0.13
    0.7%
    196
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.19
    0.06
    369
    +0.13
    0.03
    405
    +0.12
    0.05
    Negative Logits
    ESULT
    -2.07
    tered
    -1.65
    iative
    -1.53
    quier
    -1.51
    abulary
    -1.48
    achment
    -1.47
    completion
    -1.47
    mium
    -1.47
    amily
    -1.44
    mog
    -1.43
    POSITIVE LOGITS
     closely
    1.73
    amma
    1.66
    IJ
    1.66
    houses
    1.66
    orphisms
    1.65
    osph
    1.54
    orphic
    1.54
    orphism
    1.53
     indoors
    1.50
    manship
    1.50
    Activations Density 0.156%

    No Known Activations