© 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. 26572
    Prev
    Next
    INDEX
    Explanations

    elements related to guidance and advice, particularly in educational and health 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
    290
    +0.15
    0.9%
    55
    +0.13
    0.7%
    273
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.15
    0.09
    155
    +0.13
    0.15
    120
    +0.12
    0.14
    Negative Logits
     everywhere
    -1.98
     always
    -1.58
     kinda
    -1.55
     anytime
    -1.49
    fork
    -1.47
    asek
    -1.44
     EVERY
    -1.43
     damn
    -1.43
     shit
    -1.42
    istine
    -1.42
    POSITIVE LOGITS
    ème
    1.66
    ainties
    1.44
    uates
    1.39
    §
    1.36
    ĥ½
    1.36
     Lanc
    1.35
     Patients
    1.35
    tering
    1.34
     passengers
    1.33
    ceedings
    1.33
    Activations Density 2.886%

    No Known Activations