© 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. 25505
    Prev
    Next
    INDEX
    Explanations

    the name "Cass" 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
    369
    +0.18
    1.1%
    410
    +0.14
    0.8%
    191
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.18
    0.01
    437
    +0.14
    0.01
    59
    +0.14
    0.01
    Negative Logits
    rapeut
    -1.92
     importance
    -1.50
     potential
    -1.50
     slightest
    -1.47
    ollowing
    -1.45
     maternal
    -1.44
     present
    -1.43
     advice
    -1.41
    illed
    -1.41
    "?"
    -1.41
    POSITIVE LOGITS
     Square
    1.68
    idy
    1.64
    unda
    1.62
    umbered
    1.60
     encoded
    1.59
    ulence
    1.59
    obacterium
    1.51
    erne
    1.49
    illac
    1.45
    ité
    1.43
    Activations Density 0.008%

    No Known Activations