Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27467
    Prev
    Next
    INDEX
    Explanations

    references to depression and its effects on individuals

    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
    156
    +0.24
    1.4%
    71
    +0.10
    0.6%
    443
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.24
    0.01
    156
    +0.10
    0.01
    52
    +0.10
    0.01
    Negative Logits
    agles
    -1.64
    TRODUCTION
    -1.57
    uka
    -1.52
     Arabia
    -1.51
     europé
    -1.51
    stanbul
    -1.47
    '>
    -1.45
    usterity
    -1.44
    airo
    -1.43
    bey
    -1.43
    POSITIVE LOGITS
    igraph
    1.75
     scenes
    1.66
    ous
    1.59
     tolerance
    1.58
     blocker
    1.50
    table
    1.49
    isecond
    1.49
    -,
    1.49
    caster
    1.49
    ismatic
    1.47
    Activations Density 0.028%

    No Known Activations