© 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. 26913
    Prev
    Next
    INDEX
    Explanations

    greetings or informal salutations

    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
    376
    +0.14
    0.8%
    317
    +0.13
    0.7%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.14
    0.02
    78
    +0.13
    0.02
    403
    +0.12
    0.02
    Negative Logits
    ·¸
    -2.71
    ĥ½
    -2.53
    ĨĴ
    -2.52
    ¸
    -2.47
    ´
    -2.46
    ŀ
    -2.44
    ↵Č      
    -2.40
    <|outofrange|>
    -2.40
    ↵↵     
    -2.40
                                 
    -2.40
    POSITIVE LOGITS
    starter
    1.65
    ÅĽ
    1.60
    eland
    1.59
    ward
    1.48
    force
    1.47
    ji
    1.41
    quist
    1.41
    opard
    1.40
    bridge
    1.39
    rooms
    1.37
    Activations Density 0.017%

    No Known Activations