© 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 EvalsExportsAPI 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. 30514
    Prev
    Next
    INDEX
    Explanations

    references to legal or procedural terminology related to rights and responsibilities

    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
    +0.15
    0.9%
    136
    +0.12
    0.7%
    391
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.15
    0.13
    23
    +0.12
    0.13
    203
    +0.11
    0.10
    Negative Logits
    ĻĤ
    -4.13
    ¾
    -2.75
    ¿
    -2.74
    «
    -2.67
    ĨĴ
    -2.60
    ¿½
    -2.53
    ·¸
    -2.44
    ¼
    -2.42
    ĭ
    -2.36
    ħ
    -2.32
    POSITIVE LOGITS
     namely
    2.24
    omitempty
    1.92
     thereby
    1.88
    especially
    1.80
    particularly
    1.79
    namely
    1.75
     including
    1.74
    ]{}.
    1.71
     ]{}
    1.71
    ]{}
    1.70
    Activations Density 1.210%

    No Known Activations