© 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. 4-RES-SM
    11. 13444
    Prev
    Next
    INDEX
    Explanations

    narrative elements that evoke strong emotional connections, particularly related to personal experiences and animals

    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
    348
    +0.29
    1.9%
    307
    +0.28
    1.9%
    306
    +0.15
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.29
    0.23
    274
    +0.28
    0.25
    510
    +0.15
    0.24
    Negative Logits
    âĢIJ
    -1.43
    .^\[[@
    -1.26
     existed
    -1.24
     bonus
    -1.22
     taxes
    -1.20
    ubicin
    -1.18
     lasted
    -1.14
     subtract
    -1.14
     throttle
    -1.13
     playoffs
    -1.11
    POSITIVE LOGITS
     stranger
    1.47
     strangers
    1.46
     someone
    1.46
     Someone
    1.44
    asures
    1.38
    someone
    1.34
     somebody
    1.23
    idegger
    1.22
    andering
    1.22
    hello
    1.21
    Activations Density 4.828%

    No Known Activations