© 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. 26099
    Prev
    Next
    INDEX
    Explanations

    terms related to usage or employment of devices, methods, or materials

    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
    135
    +0.13
    0.8%
    102
    +0.13
    0.7%
    442
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.13
    0.03
    243
    +0.13
    0.03
    281
    +0.11
    0.01
    Negative Logits
     may
    -1.62
     success
    -1.55
     adaptations
    -1.44
     tendencies
    -1.43
     repr
    -1.43
    ()));
    -1.37
     {}
    -1.35
     thereby
    -1.35
     &=&
    -1.33
     characterize
    -1.33
    POSITIVE LOGITS
    PM
    1.54
    ^--
    1.53
    AMS
    1.52
    icorn
    1.42
    ashed
    1.39
    oma
    1.39
    awks
    1.37
    ^âĪĴ
    1.36
    ATS
    1.36
    abel
    1.36
    Activations Density 0.133%

    No Known Activations