© 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. 0-MLP-SM
    11. 26343
    Prev
    Next
    INDEX
    Explanations

    references to web technologies or web-related contexts

    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
    156
    +0.16
    0.9%
    255
    +0.12
    0.7%
    91
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.16
    0.02
    91
    +0.12
    0.02
    506
    +0.12
    0.02
    Negative Logits
     same
    -1.83
     suppose
    -1.67
     resignation
    -1.66
     declare
    -1.66
     ')
    -1.59
    ances
    -1.59
     recall
    -1.51
     Norm
    -1.46
     certain
    -1.45
     AFL
    -1.45
    POSITIVE LOGITS
    ĻĤ
    2.28
    ĸ
    2.23
    bed
    2.18
    »¿
    2.17
    ¼
    2.17
    ģ
    2.15
    ķ
    2.12
    ¾
    2.12
    ®
    2.10
    µ
    2.05
    Activations Density 0.009%

    No Known Activations