© 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. 4-RES-SM
    11. 12698
    Prev
    Next
    INDEX
    Explanations

    verbs associated with scientific investigation and analysis

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    209
    +0.14
    0.8%
    5
    +0.14
    0.8%
    330
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.14
    0.02
    5
    +0.14
    0.01
    149
    +0.13
    0.02
    Negative Logits
    »¿
    -5.45
    Ľ
    -5.30
    ¨
    -5.26
    µ
    -5.25
    ĩ
    -5.22
    ĸ´
    -5.20
    Ĩ
    -5.17
    §
    -5.13
    Ļª
    -5.12
    ĸ
    -5.12
    POSITIVE LOGITS
     retrospectively
    2.64
     immunohist
    2.60
     quantitatively
    2.47
     experimentally
    2.42
     separately
    2.35
     prospectively
    2.29
     using
    2.18
     by
    2.12
     spectrosc
    2.09
     simultaneously
    2.08
    Activations Density 0.033%

    No Known Activations