© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29505
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical properties and compositions in solutions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.31
    1.8%
    148
    +0.13
    0.8%
    282
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.31
    0.01
    156
    +0.13
    0.01
    271
    +0.12
    0.00
    Negative Logits
    olic
    -1.51
    ference
    -1.45
     Player
    -1.42
    «
    -1.37
     [...]
    -1.36
    asted
    -1.35
    rior
    -1.32
     everyone
    -1.27
     headache
    -1.26
     morale
    -1.26
    POSITIVE LOGITS
    itate
    1.68
    itarian
    1.65
    erals
    1.55
    iza
    1.52
    urious
    1.40
    "}](#
    1.37
     humour
    1.34
    brush
    1.34
    inda
    1.34
    hattan
    1.32
    Activations Density 0.042%

    No Known Activations