© 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. 2-MLP-SM
    11. 25269
    Prev
    Next
    INDEX
    Explanations

    URLs or file paths

    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
    20
    +0.13
    0.7%
    381
    +0.12
    0.7%
    91
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.13
    0.02
    207
    +0.12
    0.02
    385
    +0.12
    0.02
    Negative Logits
    ymphony
    -1.51
    vist
    -1.46
    work
    -1.43
    ondon
    -1.43
     liner
    -1.39
     zone
    -1.36
    estone
    -1.36
    ycl
    -1.35
    ored
    -1.34
    ory
    -1.33
    POSITIVE LOGITS
    idy
    1.55
    documentclass
    1.53
    culus
    1.42
    urus
    1.35
    itars
    1.34
    zos
    1.34
     retain
    1.30
    achus
    1.27
     marks
    1.27
     innocence
    1.26
    Activations Density 0.113%

    No Known Activations