© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26543
    Prev
    Next
    INDEX
    Explanations

    references to Los Angeles and related entities or places

    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
    271
    +0.18
    1.0%
    232
    +0.13
    0.7%
    85
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.18
    0.12
    23
    +0.13
    0.06
    56
    +0.13
    0.13
    Negative Logits
    \]](
    -1.72
    ="{{
    -1.71
    ocene
    -1.64
    imposed
    -1.58
    ="\
    -1.54
    ="'
    -1.49
     \-
    -1.47
    ="{
    -1.46
     "...
    -1.45
    ="
    -1.45
    POSITIVE LOGITS
    ĻĤ
    1.87
    ±
    1.66
    utor
    1.56
     lectures
    1.54
     classes
    1.44
     class
    1.41
     kernel
    1.39
    uther
    1.39
    umm
    1.38
     Catholic
    1.36
    Activations Density 3.074%

    No Known Activations