© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25543
    Prev
    Next
    INDEX
    Explanations

    negative or contradictory sentiments

    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
    23
    +0.15
    0.8%
    395
    +0.14
    0.8%
    143
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.15
    0.10
    78
    +0.14
    0.07
    395
    +0.14
    0.07
    Negative Logits
    ij
    -3.08
    Ĵ
    -2.84
    Ĥ¬
    -2.76
    §
    -2.71
    ĺ
    -2.70
    °
    -2.69
    ģ
    -2.69
    ¶
    -2.67
    ·
    -2.66
    Īĺ
    -2.65
    POSITIVE LOGITS
     alike
    2.37
     others
    1.88
    oint
    1.61
     therefrom
    1.46
    urers
    1.45
     accordingly
    1.45
     correspondingly
    1.44
     industries
    1.41
    others
    1.38
     thereafter
    1.38
    Activations Density 3.093%

    No Known Activations