© 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 EvalsExportsAPI 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. 25138
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "This" 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
    330
    +0.13
    0.7%
    475
    +0.13
    0.7%
    320
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.13
    0.02
    330
    +0.13
    0.02
    475
    +0.13
    0.02
    Negative Logits
    ever
    -1.73
    right
    -1.63
    aven
    -1.60
    roscopic
    -1.58
    located
    -1.49
    rangle
    -1.47
    ')$
    -1.46
    `,`
    -1.46
    ³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³
    -1.45
    ogether
    -1.43
    POSITIVE LOGITS
    §
    3.27
    »
    3.20
    Ń
    3.13
    ¿½
    3.11
    ¾
    3.08
    ļ
    3.05
    ĥ
    2.99
    ¡
    2.94
    ¼
    2.92
    ĵ
    2.92
    Activations Density 0.048%

    No Known Activations