© 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 EvalsExportsinterp-engineNEWAPI 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. 23744
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sources or origins

    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
    195
    +0.12
    0.7%
    237
    +0.11
    0.6%
    407
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.12
    0.10
    404
    +0.11
    0.07
    284
    +0.11
    0.06
    Negative Logits
     mess
    -1.58
     workers
    -1.50
     crim
    -1.48
    irm
    -1.47
     attackers
    -1.44
    pers
    -1.41
    oms
    -1.40
     controlling
    -1.40
    oci
    -1.37
     resilience
    -1.37
    POSITIVE LOGITS
    starter
    1.57
     Archives
    1.54
    reon
    1.50
     catalogue
    1.46
    blogger
    1.46
     acceptor
    1.46
    mouth
    1.43
    '">
    1.43
    supplementary
    1.41
     Festival
    1.40
    Activations Density 0.758%

    No Known Activations