© 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. Residuals
    9. 2-RES-SM
    11. 9970
    Prev
    Next
    INDEX
    Explanations

    terms related to systematic reviews and meta-analyses

    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/2-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.2.hook_resid_post
    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
    156
    +0.18
    1.0%
    130
    +0.13
    0.7%
    386
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.18
    0.01
    393
    +0.13
    0.01
    94
    +0.13
    0.01
    Negative Logits
     occasion
    -1.71
    oming
    -1.68
     occasions
    -1.66
     \*\**
    -1.57
    fall
    -1.49
    owed
    -1.47
     suffice
    -1.46
     overtime
    -1.46
     \*\*
    -1.45
     Respondent
    -1.44
    POSITIVE LOGITS
    ¹
    2.01
    ulates
    1.86
    het
    1.84
    °
    1.81
    £
    1.65
    »
    1.65
    achers
    1.63
    ½
    1.62
    ĻĤ
    1.61
    Ĩ
    1.60
    Activations Density 0.171%

    No Known Activations