© 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. 2-MLP-SM
    6. 25572
    Prev
    Next
    INDEX
    Explanations

    terms related to source code and programming

    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
    277
    +0.15
    0.8%
    48
    +0.14
    0.8%
    500
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.15
    0.03
    456
    +0.14
    0.01
    364
    +0.13
    0.02
    Negative Logits
     features
    -1.71
     jobs
    -1.61
    eton
    -1.60
     lives
    -1.54
    ami
    -1.49
     crafts
    -1.43
     spawn
    -1.42
    ricular
    -1.42
    enoid
    -1.39
    anian
    -1.38
    POSITIVE LOGITS
     extrad
    1.81
    Decided
    1.68
    "}](#
    1.64
     stret
    1.57
     Hö
    1.54
     Cauchy
    1.53
     Uniform
    1.49
    cibly
    1.48
    reland
    1.46
    Simplify
    1.43
    Activations Density 0.162%

    No Known Activations