© 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. 0-MLP-SM
    11. 26891
    Prev
    Next
    INDEX
    Explanations

    references to being saved or rescued from negative situations

    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
    +0.18
    1.0%
    148
    +0.14
    0.8%
    415
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.18
    0.02
    415
    +0.14
    0.02
    141
    +0.12
    0.02
    Negative Logits
    onson
    -1.72
    oved
    -1.50
     okay
    -1.44
    omorphism
    -1.41
    ish
    -1.37
    ]>
    -1.37
     characterised
    -1.34
     dioxide
    -1.34
    olic
    -1.33
    oured
    -1.33
    POSITIVE LOGITS
    InstanceState
    2.36
    ł
    1.77
    holder
    1.70
    ¤
    1.62
    ĻĤ
    1.47
    ĸ
    1.47
    ĺ
    1.47
    mmc
    1.43
     occasion
    1.42
    ļ
    1.41
    Activations Density 0.038%

    No Known Activations