© 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. 11213
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and specialized 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
    21
    +0.39
    2.5%
    255
    +0.15
    1.0%
    70
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.39
    0.07
    255
    +0.15
    0.00
    98
    +0.12
    0.03
    Negative Logits
     added
    -1.39
     avail
    -1.39
     United
    -1.35
     ++
    -1.28
     supreme
    -1.27
    itsu
    -1.26
     trust
    -1.25
    irl
    -1.21
    adder
    -1.20
    IBLE
    -1.20
    POSITIVE LOGITS
    ĻĤ
    3.53
    ħ
    3.50
    ģ
    3.50
    Ħ
    3.27
    ĺ
    3.19
    Ĩ
    3.06
    ł
    3.05
    ĥ
    3.04
    Ļ
    2.97
    Ĭ
    2.96
    Activations Density 0.453%

    No Known Activations