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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26695
    Prev
    Next
    INDEX
    Explanations

    emotions and themes related to struggle, redemption, and complexity in human experience

    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
    428
    +0.12
    0.7%
    431
    +0.11
    0.6%
    341
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.12
    0.14
    277
    +0.11
    0.12
    168
    +0.10
    0.10
    Negative Logits
    )!
    -1.78
     inspiration
    -1.59
     walls
    -1.57
     apart
    -1.51
     fasc
    -1.51
    )?
    -1.47
     dimensional
    -1.40
    dimensional
    -1.39
     illustrative
    -1.39
     notch
    -1.39
    POSITIVE LOGITS
    >]
    1.70
    ]{.
    1.56
    mund
    1.45
    edes
    1.41
    >"
    1.40
    >",
    1.39
    "`
    1.38
    ux
    1.37
    >>>>
    1.36
    dbc
    1.36
    Activations Density 2.051%

    No Known Activations