© 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. 29738
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "anthropology" or its variations

    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
    356
    +0.13
    0.7%
    259
    +0.12
    0.6%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.13
    0.01
    142
    +0.12
    0.01
    321
    +0.11
    0.01
    Negative Logits
    ¿
    -4.03
    ĨĴ
    -3.60
    ĵ
    -3.33
    ´
    -3.32
    ĭ
    -3.29
    Ĺ
    -3.26
    «
    -3.26
    ·¸
    -3.25
    Īĺ
    -3.24
    ¬
    -3.24
    POSITIVE LOGITS
    iary
    1.58
     fiction
    1.55
    onymous
    1.55
    rum
    1.45
    inates
    1.44
    smith
    1.42
    obacterium
    1.40
    rop
    1.40
    onym
    1.39
     =>
    1.39
    Activations Density 1.637%

    No Known Activations