© 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. 26396
    Prev
    Next
    INDEX
    Explanations

    references to high schools

    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
    446
    +0.13
    0.7%
    444
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.13
    0.04
    446
    +0.12
    0.02
    254
    +0.12
    0.02
    Negative Logits
    ĭ
    -4.16
    ĥ½
    -4.01
    <|outofrange|>
    -3.93
     ↵
    -3.93
    <|outofrange|>
    -3.93
    ↵
    -3.93
              ↵
    -3.93
    ↵
    -3.93
    -3.93
    <|outofrange|>
    -3.93
    POSITIVE LOGITS
    forth
    1.34
     linearity
    1.31
    ainen
    1.30
     deviation
    1.30
    ichte
    1.29
    bia
    1.27
    okes
    1.26
    eks
    1.25
    ais
    1.25
    omit
    1.24
    Activations Density 0.189%

    No Known Activations