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

    Neuronpedia

    Jacobian LensNEW
    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. 28390
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "un" indicating negation or reversal

    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
    377
    +0.18
    1.0%
    375
    +0.13
    0.7%
    369
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.18
    0.06
    375
    +0.13
    0.06
    426
    +0.13
    0.05
    Negative Logits
    ubottu
    -1.69
    oretic
    -1.63
    lication
    -1.58
    las
    -1.52
     successive
    -1.44
     separate
    -1.41
     respective
    -1.38
     apert
    -1.33
    mia
    -1.31
    separ
    -1.31
    POSITIVE LOGITS
    Īĺ
    2.54
    µ
    2.31
    ½
    2.18
    Ł
    2.17
    ĻĤ
    2.16
    ²
    2.12
    ·
    2.11
    ³
    2.10
    ·¸
    2.08
    ©
    2.06
    Activations Density 0.027%

    No Known Activations