© 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 EvalsExportsAPI 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. 29344
    Prev
    Next
    INDEX
    Explanations

    phrases indicating range or extent, particularly in time or space

    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
    376
    +0.19
    1.1%
    115
    +0.14
    0.8%
    181
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.19
    0.01
    186
    +0.14
    0.01
    265
    +0.12
    0.01
    Negative Logits
    že
    -1.45
    oqu
    -1.44
    ands
    -1.38
    ux
    -1.38
    schen
    -1.37
     choosing
    -1.33
     ORDERED
    -1.32
    esy
    -1.31
    given
    -1.30
    lev
    -1.30
    POSITIVE LOGITS
     generations
    1.54
     (>
    1.39
     vertebra
    1.37
    osus
    1.37
    imal
    1.36
     among
    1.36
    bones
    1.34
     ]
    1.34
    ences
    1.34
    tee
    1.31
    Activations Density 0.055%

    No Known Activations