© 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. 2-RES-SM
    6. 30302
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to licensing

    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
    320
    +0.12
    0.7%
    222
    +0.12
    0.7%
    192
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.12
    0.02
    222
    +0.12
    0.02
    453
    +0.12
    0.02
    Negative Logits
    esque
    -1.66
    ths
    -1.62
    ensional
    -1.43
     floats
    -1.43
    #{$
    -1.42
    umin
    -1.39
     alike
    -1.38
    ographic
    -1.35
    aney
    -1.34
    oge
    -1.32
    POSITIVE LOGITS
     license
    1.63
    Ħ
    1.62
    Lic
    1.61
     lic
    1.56
    ¸
    1.53
     licenses
    1.50
    Ĥ
    1.48
    iella
    1.44
    License
    1.43
     expire
    1.43
    Activations Density 0.036%

    No Known Activations