© 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. 23121
    Prev
    Next
    INDEX
    Explanations

    reflections on self-identity and self-awareness

    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
    131
    +0.12
    0.6%
    12
    +0.10
    0.6%
    373
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.12
    0.03
    131
    +0.10
    0.04
    373
    +0.10
    0.04
    Negative Logits
    ĩ
    -2.58
    ľĵ
    -2.28
    £
    -2.24
    Ĩ
    -2.24
    ĻĤ
    -2.22
    ¿
    -2.15
    İ
    -2.08
    ĥ½
    -2.05
    Ĺ
    -2.04
    °
    -2.01
    POSITIVE LOGITS
    ney
    1.56
    cember
    1.46
    borough
    1.39
    cki
    1.37
     resumed
    1.35
    blockList
    1.30
    ked
    1.30
    amycin
    1.30
    Click
    1.29
    ursday
    1.27
    Activations Density 0.277%

    No Known Activations