© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 30052
    Prev
    Next
    INDEX
    Explanations

    terms related to duties and responsibilities

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    423
    +0.13
    0.7%
    219
    +0.12
    0.6%
    42
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.13
    0.01
    423
    +0.12
    0.01
    72
    +0.12
    0.01
    Negative Logits
     anything
    -1.52
    illance
    -1.50
    ANS
    -1.46
     respect
    -1.44
    rage
    -1.42
    ITED
    -1.38
     spite
    -1.34
    usion
    -1.32
     hesitate
    -1.30
    IGHT
    -1.30
    POSITIVE LOGITS
    borg
    1.63
    umbs
    1.61
    inces
    1.53
    bugs
    1.51
    fileID
    1.50
    enos
    1.45
    components
    1.45
    efs
    1.43
    fing
    1.41
    elist
    1.41
    Activations Density 0.123%

    No Known Activations