© 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. 24266
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial decisions

    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
    +0.26
    1.5%
    271
    +0.18
    1.0%
    136
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.26
    0.32
    111
    +0.18
    0.29
    271
    +0.13
    -0.11
    Negative Logits
    sson
    -1.65
    "...
    -1.64
    matic
    -1.49
    ")]
    -1.46
     WARRANTIES
    -1.45
    "?"
    -1.41
    "?
    -1.40
    \]\].
    -1.39
    ...](
    -1.38
    %).
    -1.37
    POSITIVE LOGITS
    ĻĤ
    3.45
    ģ
    3.26
    »¿
    3.18
    »
    3.14
    ĺ
    3.10
    ĵ
    3.05
    ¦
    3.02
    ĥ
    2.99
    ľĵ
    2.94
    Īĺ
    2.89
    Activations Density 13.763%

    No Known Activations