© 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. 26376
    Prev
    Next
    INDEX
    Explanations

    events and case details from legal documents

    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
    47
    +0.13
    0.7%
    253
    +0.11
    0.6%
    32
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.13
    0.04
    318
    +0.11
    0.03
    253
    +0.10
    0.04
    Negative Logits
    ally
    -1.81
    iflu
    -1.77
     remedies
    -1.63
    alent
    -1.54
    rapeut
    -1.52
     disse
    -1.36
     harb
    -1.36
    isciplinary
    -1.36
    unci
    -1.33
    isse
    -1.33
    POSITIVE LOGITS
    ipers
    1.65
    Ĵ
    1.58
     Teams
    1.50
    ĸ
    1.47
     Mice
    1.45
     Rangers
    1.44
    ¤
    1.43
    Īĺ
    1.43
     Hawks
    1.42
    ¼
    1.39
    Activations Density 0.067%

    No Known Activations