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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27114
    Prev
    Next
    INDEX
    Explanations

    phrases indicating public opinion and political dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.18
    1.0%
    271
    +0.16
    0.9%
    187
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.18
    -0.01
    187
    +0.16
    0.11
    142
    +0.11
    0.04
    Negative Logits
    heets
    -1.95
    ktop
    -1.51
    itars
    -1.50
    achus
    -1.49
    osyl
    -1.47
    ulty
    -1.47
    hores
    -1.42
    swer
    -1.41
    denly
    -1.40
    alion
    -1.38
    POSITIVE LOGITS
    ĵ
    1.46
    >`
    1.44
     worth
    1.42
    ]{}.
    1.40
    £
    1.40
    ]>
    1.35
     history
    1.30
    ].
    1.29
     toxicity
    1.28
    aku
    1.26
    Activations Density 7.350%

    No Known Activations