© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25949
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the lack of warranty or guarantee in software licenses

    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
    342
    +0.15
    0.8%
    156
    +0.11
    0.6%
    174
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.15
    0.02
    342
    +0.11
    0.01
    248
    +0.11
    0.01
    Negative Logits
    olation
    -1.70
    ahoo
    -1.54
    oshi
    -1.46
    vertis
    -1.39
    quisition
    -1.38
    oso
    -1.38
    ologist
    -1.38
    nesty
    -1.33
    apters
    -1.32
    ppat
    -1.32
    POSITIVE LOGITS
    ½
    3.78
    ©
    3.65
    »
    3.62
    Ń
    3.55
    §
    3.54
    ¿
    3.50
    Į
    3.48
    °
    3.46
    ı
    3.44
    Ĩ
    3.42
    Activations Density 0.042%

    No Known Activations