© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26530
    Prev
    Next
    INDEX
    Explanations

    technical specifications or attributes related to software or hardware configurations

    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
    376
    +0.13
    0.7%
    43
    +0.11
    0.6%
    59
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.13
    0.09
    376
    +0.11
    0.08
    59
    +0.10
    0.03
    Negative Logits
    rangle
    -1.50
    urgical
    -1.40
    idyl
    -1.39
    uters
    -1.39
     decorated
    -1.37
    ASK
    -1.36
     travers
    -1.34
     murdered
    -1.34
     ')
    -1.34
     vacant
    -1.32
    POSITIVE LOGITS
    ·¸
    3.38
    ī
    3.25
    Ħ
    3.22
    «
    3.18
    ·
    3.17
    ³
    3.14
    ²
    3.02
    ł
    2.97
    ¾
    2.94
    ½
    2.90
    Activations Density 0.306%

    No Known Activations