© 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. 28166
    Prev
    Next
    INDEX
    Explanations

    words related to legal justice and exoneration

    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
    344
    +0.12
    0.7%
    86
    +0.12
    0.7%
    90
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.06
    494
    +0.12
    0.04
    23
    +0.11
    0.05
    Negative Logits
    "`
    -1.79
     developing
    -1.63
     greater
    -1.58
    omitempty
    -1.55
    >';
    -1.54
     liking
    -1.50
    anson
    -1.44
    Developer
    -1.44
    ighter
    -1.44
     Respondent
    -1.40
    POSITIVE LOGITS
    etable
    1.82
    iem
    1.81
    ariate
    1.71
    iative
    1.68
    ie
    1.63
    eria
    1.62
    ectomy
    1.59
     aisle
    1.57
    ieux
    1.57
    cule
    1.57
    Activations Density 3.667%

    No Known Activations