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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 25986
    Prev
    Next
    INDEX
    Explanations

    themes related to power dynamics and relationships in narratives

    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
    365
    +0.12
    0.7%
    317
    +0.11
    0.7%
    336
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.04
    336
    +0.11
    0.06
    317
    +0.10
    0.08
    Negative Logits
    soever
    -1.46
     Schedule
    -1.46
    stadt
    -1.40
    ħ
    -1.39
    ŀ
    -1.39
     sanctions
    -1.37
     waived
    -1.33
    wealth
    -1.33
     formulation
    -1.32
     law
    -1.32
    POSITIVE LOGITS
    rame
    1.48
    amo
    1.47
     circumference
    1.46
    hour
    1.42
     %>
    1.40
    achi
    1.40
    á̝
    1.39
     hour
    1.39
    ://
    1.38
    daily
    1.36
    Activations Density 2.012%

    No Known Activations