© 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. MLP Post
    9. 2-MLP-SM
    11. 24685
    Prev
    Next
    INDEX
    Explanations

    terms related to guidance and direction 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/2-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.2.hook_mlp_out
    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
    476
    +0.13
    0.7%
    265
    +0.11
    0.6%
    465
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.13
    0.03
    297
    +0.11
    0.04
    145
    +0.11
    0.03
    Negative Logits
    places
    -1.73
     onward
    -1.56
     shootings
    -1.53
     relapse
    -1.50
     biopsies
    -1.49
     marked
    -1.48
    rogens
    -1.44
     biopsy
    -1.44
     facilitated
    -1.43
     progressing
    -1.42
    POSITIVE LOGITS
    inho
    2.02
    enda
    1.88
    iator
    1.85
    eur
    1.84
    endor
    1.83
    rico
    1.83
    ição
    1.82
    iative
    1.82
    ↵³³
    1.81
    lotte
    1.80
    Activations Density 0.478%

    No Known Activations