© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30361
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "str"

    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
    141
    +0.14
    0.8%
    410
    +0.13
    0.7%
    269
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.14
    0.02
    250
    +0.13
    0.02
    77
    +0.13
    0.01
    Negative Logits
     behalf
    -1.96
    cretion
    -1.55
    esian
    -1.53
    ľĵ
    -1.53
    hire
    -1.53
    ĥ
    -1.53
     particular
    -1.51
     myself
    -1.51
    izumab
    -1.49
     specific
    -1.47
    POSITIVE LOGITS
    ategy
    2.07
    cpy
    1.84
    addle
    1.81
    ftime
    1.81
    dup
    1.79
    anged
    1.75
    ich
    1.69
    ungen
    1.68
    tok
    1.62
    anges
    1.59
    Activations Density 0.121%

    No Known Activations