© 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. 2-MLP-SM
    11. 26527
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of disagreement

    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
    176
    +0.13
    0.7%
    454
    +0.12
    0.7%
    387
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.13
    0.03
    266
    +0.12
    0.02
    130
    +0.12
    0.07
    Negative Logits
    |_
    -1.63
    eness
    -1.50
    |_{
    -1.48
    |^{
    -1.45
    ]:
    -1.45
     inactivated
    -1.44
    |^
    -1.44
    atase
    -1.40
    ateness
    -1.40
    rapy
    -1.39
    POSITIVE LOGITS
    oft
    1.65
     genre
    1.54
    person
    1.53
    nem
    1.52
    ressor
    1.49
    enger
    1.42
     exception
    1.41
    obl
    1.40
    agn
    1.40
     genres
    1.39
    Activations Density 0.580%

    No Known Activations