© 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. 25978
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and components related to software and programming

    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
    226
    +0.13
    0.7%
    181
    +0.12
    0.6%
    232
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.06
    112
    +0.12
    0.12
    232
    +0.11
    0.11
    Negative Logits
     herself
    -1.68
    »
    -1.66
    ¼
    -1.61
    ivia
    -1.50
    ī
    -1.45
     themselves
    -1.44
     Gaza
    -1.42
     Id
    -1.41
     advantage
    -1.40
     enemy
    -1.39
    POSITIVE LOGITS
    lace
    1.60
    havior
    1.48
    cribing
    1.45
     <<
    1.43
    nop
    1.42
    quote
    1.42
    BPF
    1.26
     assim
    1.26
    sever
    1.26
    ABA
    1.25
    Activations Density 4.226%

    No Known Activations