© 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. 22848
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'n' in the text

    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
    +0.17
    1.0%
    77
    +0.16
    0.9%
    275
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.17
    0.03
    275
    +0.16
    0.01
    427
    +0.14
    0.04
    Negative Logits
    journal
    -1.80
    body
    -1.59
    CLUDING
    -1.56
     assistants
    -1.46
    VENT
    -1.45
    ressing
    -1.40
    clock
    -1.37
     assistant
    -1.36
    herin
    -1.35
    heter
    -1.35
    POSITIVE LOGITS
    §
    2.22
    ±
    2.21
    Ĺ
    2.19
    ³
    2.16
    ¯
    2.09
    º
    2.09
    »
    2.08
    ·
    2.02
    IJ
    1.99
    ¶
    1.98
    Activations Density 0.165%

    No Known Activations