© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 12535
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in structured data formats, particularly JSON or XML-like structures

    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
    479
    +0.18
    1.0%
    326
    +0.14
    0.8%
    74
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.18
    0.10
    0
    +0.14
    0.11
    345
    +0.13
    0.10
    Negative Logits
     yours
    -1.60
    >();
    -1.53
    inib
    -1.51
    irez
    -1.46
    àµį
    -1.44
     talented
    -1.42
    à°¿
    -1.42
    ++)
    -1.40
    procedure
    -1.39
    orna
    -1.37
    POSITIVE LOGITS
    oken
    1.45
    inition
    1.37
     infancy
    1.33
    days
    1.30
    ableness
    1.30
    KY
    1.28
    hood
    1.27
     domains
    1.26
     ordinal
    1.26
     pounds
    1.24
    Activations Density 3.589%

    No Known Activations