© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 25481
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    433
    +0.13
    0.7%
    321
    +0.12
    0.7%
    422
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.45
    209
    +0.12
    0.29
    402
    +0.12
    0.26
    Negative Logits
    ¿½
    -2.86
    ´
    -2.82
    ®
    -2.79
    µ
    -2.54
    Ĭ
    -2.53
    ·¸
    -2.41
    ĥ
    -2.38
    ¶
    -2.38
    °
    -2.36
    »
    -2.35
    POSITIVE LOGITS
     alone
    1.79
    ious
    1.52
     infiltr
    1.47
    ring
    1.44
    vereign
    1.44
     HN
    1.42
    rypt
    1.41
    ling
    1.40
    vable
    1.36
    rip
    1.35
    Activations Density 1.562%

    No Known Activations