© 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. 24727
    Prev
    Next
    INDEX
    Explanations

    terms related to migration and movement

    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
    +0.15
    0.8%
    381
    +0.13
    0.7%
    430
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.15
    0.02
    430
    +0.13
    0.01
    156
    +0.10
    0.02
    Negative Logits
    ĥ
    -2.34
    º
    -2.14
    ĸ´
    -2.04
    §
    -1.97
    ¯
    -1.94
    ķ
    -1.94
    Ĥ¬
    -1.91
    ying
    -1.82
    ĥ½
    -1.82
    »¿
    -1.81
    POSITIVE LOGITS
    ceral
    1.82
     controls
    1.71
    InstanceState
    1.58
    dal
    1.53
     towards
    1.53
    iens
    1.52
    ient
    1.50
     arte
    1.47
    ropolis
    1.44
    gap
    1.41
    Activations Density 0.101%

    No Known Activations