© 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. 23881
    Prev
    Next
    INDEX
    Explanations

    specific names or terms ending with "ina" or similar variations

    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
    23
    +0.27
    1.6%
    423
    +0.10
    0.6%
    154
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.27
    0.07
    332
    +0.10
    0.08
    105
    +0.10
    0.06
    Negative Logits
    wagen
    -1.67
    İ
    -1.58
    ocur
    -1.54
    Ń
    -1.51
     retains
    -1.49
    IJ
    -1.46
    venue
    -1.44
     poses
    -1.41
    zent
    -1.41
     limitation
    -1.37
    POSITIVE LOGITS
    llll
    1.87
    hin
    1.56
    thood
    1.54
    ITED
    1.52
    ISHED
    1.51
    ÑģÑĮ
    1.50
     READ
    1.43
    |=
    1.41
    STEM
    1.40
    reate
    1.39
    Activations Density 0.508%

    No Known Activations