© 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. 29994
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    436
    +0.14
    0.8%
    280
    +0.14
    0.8%
    332
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.14
    0.45
    209
    +0.14
    0.29
    402
    +0.13
    0.26
    Negative Logits
    overs
    -1.61
     brake
    -1.39
     idle
    -1.31
    vals
    -1.30
    (['
    -1.28
     bay
    -1.26
     clutch
    -1.23
    arly
    -1.22
     judgement
    -1.22
     jet
    -1.21
    POSITIVE LOGITS
    cle
    1.81
    quier
    1.78
    aling
    1.75
    coding
    1.59
    ching
    1.58
    eto
    1.58
    laughs
    1.57
    tern
    1.57
    ending
    1.55
    tered
    1.53
    Activations Density 1.578%

    No Known Activations

    This feature has no known activations.