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. 29534
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to software development, particularly in the Symfony framework

    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
    419
    +0.24
    1.4%
    379
    +0.13
    0.7%
    317
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.24
    0.07
    253
    +0.13
    0.04
    21
    +0.12
    0.03
    Negative Logits
    Īĺ
    -2.15
    heet
    -1.90
    heets
    -1.65
    illed
    -1.55
    icolor
    -1.44
     caller
    -1.38
     possessions
    -1.32
    ĻĤ
    -1.31
    woke
    -1.31
    outs
    -1.31
    POSITIVE LOGITS
    "}](#
    1.63
    ingen
    1.53
    ÂĶ
    1.50
    essential
    1.42
    instein
    1.39
    hard
    1.37
    heimer
    1.35
    king
    1.30
    )\]
    1.29
    â
    1.29
    Activations Density 0.797%

    No Known Activations