© 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. 2-RES-SM
    11. 14022
    Prev
    Next
    INDEX
    Explanations

    statements reflecting critical reasoning about systems and their functionalities

    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
    478
    +0.15
    0.9%
    369
    +0.14
    0.8%
    438
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.15
    0.08
    53
    +0.14
    0.06
    400
    +0.13
    0.03
    Negative Logits
    ]{.
    -1.70
    ]:
    -1.60
     ]"
    -1.51
    ız
    -1.42
     */
    -1.41
    omics
    -1.40
    hard
    -1.38
    yz
    -1.31
    opa
    -1.30
    acks
    -1.29
    POSITIVE LOGITS
    Č
    1.63
    Writ
    1.52
    Moreover
    1.47
    Furthermore
    1.45
    inher
    1.44
    Indeed
    1.43
    existence
    1.42
    procedure
    1.38
     fruitful
    1.38
     numerous
    1.37
    Activations Density 0.503%

    No Known Activations