© 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. 26158
    Prev
    Next
    INDEX
    Explanations

    references to digital technology and its applications

    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
    348
    +0.14
    0.8%
    260
    +0.13
    0.7%
    10
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.03
    260
    +0.13
    0.03
    334
    +0.13
    0.02
    Negative Logits
    hth
    -1.45
    \)
    -1.43
    HT
    -1.40
     stripped
    -1.39
     finding
    -1.39
     assured
    -1.37
     reminded
    -1.32
     ensured
    -1.30
     plotted
    -1.28
     RH
    -1.25
    POSITIVE LOGITS
    ifornia
    1.78
    caster
    1.78
     Pradesh
    1.77
    InstanceState
    1.71
    commons
    1.66
    brains
    1.64
    irtual
    1.61
    ctors
    1.59
    casters
    1.55
    isse
    1.54
    Activations Density 0.067%

    No Known Activations