© 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. 12511
    Prev
    Next
    INDEX
    Explanations

    specific personal information required for identification and account management

    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
    17
    +0.16
    0.9%
    307
    +0.14
    0.8%
    358
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.40
    156
    +0.14
    0.30
    71
    +0.12
    0.26
    Negative Logits
    ystems
    -1.66
     outwe
    -1.59
    **--**
    -1.42
     conver
    -1.41
     ourselves
    -1.40
    hores
    -1.39
     converge
    -1.36
     rats
    -1.35
    olev
    -1.34
    raiser
    -1.28
    POSITIVE LOGITS
     surname
    3.45
     dates
    2.81
     date
    2.76
     name
    2.61
    urname
    2.59
     names
    2.46
     nationality
    2.46
     username
    2.39
     nickname
    2.39
     address
    2.38
    Activations Density 1.328%

    No Known Activations