© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27197
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and."

    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
    463
    +0.14
    0.8%
    339
    +0.12
    0.6%
    189
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.14
    0.45
    209
    +0.12
    0.29
    402
    +0.11
    0.26
    Negative Logits
    over
    -1.31
    för
    -1.29
    houses
    -1.27
     mice
    -1.26
    caster
    -1.26
    friends
    -1.23
    casters
    -1.23
    ↵
    -1.21
     Algorithm
    -1.19
    making
    -1.19
    POSITIVE LOGITS
    eron
    1.50
     favor
    1.44
    role
    1.42
    idone
    1.41
     rele
    1.40
    roviral
    1.36
     entirety
    1.36
    iano
    1.35
    .[
    1.35
    ppo
    1.35
    Activations Density 1.570%

    No Known Activations