© 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. 2-MLP-SM
    11. 23237
    Prev
    Next
    INDEX
    Explanations

    expressions of capability or potential in various 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/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
    324
    +0.16
    0.9%
    424
    +0.15
    0.9%
    92
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.16
    0.04
    58
    +0.15
    0.05
    335
    +0.12
    0.05
    Negative Logits
    ulp
    -1.58
     together
    -1.53
    ebra
    -1.51
    III
    -1.51
    II
    -1.47
     suffice
    -1.45
    efs
    -1.45
    ength
    -1.42
    IPS
    -1.41
    undef
    -1.41
    POSITIVE LOGITS
    Ĵ
    3.28
    ½
    3.04
    ¨
    2.80
    ¢
    2.80
    ī
    2.78
    Ģ
    2.77
    ·¸
    2.76
    ¸
    2.73
    ŀ
    2.71
    ļ
    2.58
    Activations Density 0.409%

    No Known Activations