© 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. 24767
    Prev
    Next
    INDEX
    Explanations

    negative adjectives and descriptions related to behavior and character

    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
    246
    +0.13
    0.7%
    225
    +0.11
    0.6%
    112
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.13
    0.08
    277
    +0.11
    0.08
    456
    +0.10
    0.01
    Negative Logits
    ĻĤ
    -2.08
     least
    -1.39
    unk
    -1.38
    ±
    -1.36
    {})
    -1.34
     outright
    -1.32
     slightest
    -1.31
     anything
    -1.30
    oven
    -1.30
     left
    -1.30
    POSITIVE LOGITS
    Fore
    1.51
     Appeal
    1.45
    '>
    1.29
     website
    1.29
     Literature
    1.29
    dern
    1.28
     Forest
    1.24
     '</
    1.24
    orship
    1.22
    oxylin
    1.22
    Activations Density 0.980%

    No Known Activations