Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26135
    Prev
    Next
    INDEX
    Explanations

    terms related to cell differentiation processes

    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
    225
    +0.12
    0.6%
    7
    +0.11
    0.6%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.12
    0.05
    225
    +0.11
    0.03
    250
    +0.11
    0.02
    Negative Logits
    Ļ
    -2.96
    ¿
    -2.85
    Ł
    -2.82
    ķ
    -2.81
    Ĺ
    -2.77
    ¥
    -2.67
    ¹
    -2.67
    ľĵ
    -2.56
    č↵    
    -2.56
    <|outofrange|>
    -2.56
    POSITIVE LOGITS
     (_
    1.88
     decomposed
    1.78
    "}](#
    1.68
     signed
    1.57
     symbolic
    1.52
     decorated
    1.50
     learned
    1.45
     ];
    1.44
     named
    1.44
     #"
    1.43
    Activations Density 0.359%

    No Known Activations