© 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. 13443
    Prev
    Next
    INDEX
    Explanations

    quotes and punctuation marks in the text

    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
    23
    +0.17
    1.0%
    124
    +0.12
    0.7%
    89
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.17
    0.05
    89
    +0.12
    0.05
    23
    +0.12
    0.06
    Negative Logits
    ·¸
    -1.84
    ļ
    -1.60
    ↵↵
    -1.59
    ↵
    -1.59
    ↵
    -1.59
    -1.59
    ↵↵↵
    -1.59
                  ↵
    -1.59
     ↵
    -1.59
    ↵
    -1.59
    POSITIVE LOGITS
     Then
    1.62
    ?'
    1.56
    ↵
    1.46
     ];
    1.43
    "`
    1.42
    ↵
    1.41
    }}'
    1.39
    ↵
    1.38
    Submitted
    1.38
     ,"
    1.34
    Activations Density 0.300%

    No Known Activations