© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27863
    Prev
    Next
    INDEX
    Explanations

    hashtags and social media campaign references

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    478
    +0.11
    0.6%
    58
    +0.10
    0.6%
    87
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    42
    +0.11
    0.03
    155
    +0.10
    0.03
    58
    +0.10
    0.03
    Negative Logits
     outset
    -1.70
     spot
    -1.63
     respectively
    -1.55
     opened
    -1.53
     remote
    -1.47
     properties
    -1.44
    respectively
    -1.43
     vacated
    -1.40
    ardless
    -1.39
     property
    -1.37
    POSITIVE LOGITS
    ¼
    3.47
    Į
    3.34
    ½
    3.17
    ¹
    3.16
    Ĭ
    3.11
    ¸
    3.11
    ĻĤ
    3.04
    Ķ
    3.04
    ·
    3.00
    ·¸
    3.00
    Activations Density 0.375%

    No Known Activations