© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27890
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we" and the phrase "On 10"

    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
    220
    +0.12
    0.7%
    172
    +0.12
    0.7%
    86
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.17
    152
    +0.12
    0.15
    425
    +0.10
    0.13
    Negative Logits
    lessness
    -1.70
    minster
    -1.47
    ~.
    -1.38
    iculously
    -1.38
    ~,
    -1.36
    caster
    -1.35
    romy
    -1.34
     Aircraft
    -1.33
     Circuit
    -1.31
    isher
    -1.31
    POSITIVE LOGITS
    pered
    1.80
    ored
    1.71
     lengths
    1.56
    hered
    1.55
    Äĩ
    1.54
     ours
    1.48
    ppa
    1.44
     whit
    1.41
    ams
    1.40
    oring
    1.39
    Activations Density 0.625%

    No Known Activations