© 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. 27158
    Prev
    Next
    INDEX
    Explanations

    references to inclusivity or collective experiences involving "everyone"

    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
    94
    +0.11
    0.6%
    333
    +0.11
    0.6%
    363
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.11
    0.04
    356
    +0.11
    0.05
    216
    +0.10
    0.04
    Negative Logits
     Âĵ
    -1.60
    ronic
    -1.48
    []
    -1.46
     persu
    -1.44
    lich
    -1.44
    stood
    -1.43
     \[[
    -1.43
     enough
    -1.40
    ught
    -1.36
    .\[[@
    -1.36
    POSITIVE LOGITS
    cation
    1.47
    mol
    1.45
    iper
    1.42
    åĬ¡
    1.41
    oda
    1.40
    Tax
    1.38
    }$-
    1.38
    $}
    1.35
    Au
    1.31
    $-
    1.26
    Activations Density 0.100%

    No Known Activations