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

    Neuronpedia

    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. 25364
    Prev
    Next
    INDEX
    Explanations

    references to walls or barriers 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
    233
    +0.15
    0.8%
    380
    +0.12
    0.7%
    274
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.15
    0.09
    55
    +0.12
    0.04
    151
    +0.11
    0.07
    Negative Logits
    £
    -2.16
    Ļ
    -2.09
    ŀ
    -1.90
    ĸ
    -1.90
    ¾
    -1.79
    ĵ
    -1.78
    ļ
    -1.76
    Ľ
    -1.76
    µ
    -1.71
    ·¸
    -1.71
    POSITIVE LOGITS
    \":
    1.70
    =”
    1.66
    \",
    1.66
    iture
    1.64
    âĢ³
    1.59
    ”,
    1.57
    ”:
    1.57
    fficients
    1.50
    ocations
    1.47
    atura
    1.47
    Activations Density 1.767%

    No Known Activations