© 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. 22734
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive outcomes and achievements

    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
    102
    +0.15
    0.9%
    250
    +0.12
    0.7%
    98
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.15
    0.13
    102
    +0.12
    0.07
    422
    +0.11
    0.11
    Negative Logits
    lying
    -1.43
     projecting
    -1.39
    olly
    -1.31
     imposing
    -1.29
    oses
    -1.27
     knocking
    -1.26
     marking
    -1.22
     prone
    -1.20
     swelling
    -1.20
    gered
    -1.19
    POSITIVE LOGITS
    ↵
    1.32
    bies
    1.32
    "}](#
    1.31
     */,
    1.26
    idium
    1.21
     Reviews
    1.19
    ]{.
    1.19
    ↵
    1.19
     Magazine
    1.19
    }})$.
    1.19
    Activations Density 1.639%

    No Known Activations