© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27850
    Prev
    Next
    INDEX
    Explanations

    specific legal terminology or phrases

    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
    111
    +0.13
    0.7%
    410
    +0.13
    0.7%
    243
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.13
    0.26
    438
    +0.13
    0.24
    56
    +0.12
    0.06
    Negative Logits
     ?"
    -1.75
     ")
    -1.62
     };
    -1.60
     endl
    -1.49
     distance
    -1.44
     },
    -1.43
     disciples
    -1.39
     ",
    -1.38
     \\
    -1.35
     });
    -1.32
    POSITIVE LOGITS
    ENTIAL
    1.72
    enstein
    1.61
    cores
    1.50
     correlates
    1.48
    caster
    1.44
    etto
    1.43
    tee
    1.41
    ellar
    1.40
    itas
    1.39
    grounds
    1.38
    Activations Density 4.812%

    No Known Activations