© 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. 2-MLP-SM
    11. 26815
    Prev
    Next
    INDEX
    Explanations

    categories related to adult content or explicit themes

    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
    237
    +0.13
    0.7%
    54
    +0.11
    0.6%
    143
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.13
    0.01
    113
    +0.11
    0.01
    82
    +0.11
    0.01
    Negative Logits
    \":
    -1.93
    oslav
    -1.82
    zza
    -1.57
    =\"
    -1.50
     Than
    -1.48
    zzo
    -1.47
    ÅĦ
    -1.42
    imiento
    -1.41
    ":
    -1.37
    imes
    -1.36
    POSITIVE LOGITS
    Ĵ
    3.46
    Ĭ
    3.45
    §
    3.45
    IJ
    3.37
    ↵
    3.33
    3.33
    ↵↵
    3.33
    3.33
    č↵
    3.33
    ↵↵
    3.33
    Activations Density 0.023%

    No Known Activations