© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-MLP-SM
    11. 24947
    Prev
    Next
    INDEX
    Explanations

    references to electrical components and their configurations

    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
    411
    +0.14
    0.8%
    480
    +0.13
    0.7%
    443
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.14
    0.02
    480
    +0.13
    0.02
    291
    +0.11
    0.02
    Negative Logits
     whisk
    -1.63
    ^(
    -1.57
    Patent
    -1.49
    resis
    -1.46
    func
    -1.43
     rect
    -1.40
    procedure
    -1.39
     applicant
    -1.38
    cept
    -1.37
     lubric
    -1.37
    POSITIVE LOGITS
    Ĥ¬
    3.38
    Ĵ
    3.16
    ¹
    3.15
    º
    3.10
    ¶
    3.09
    3.07
    ↵            ↵
    3.07
    ↵
    3.07
    ↵
    3.07
    <|outofrange|>
    3.07
    Activations Density 0.096%

    No Known Activations