Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29022
    Prev
    Next
    INDEX
    Explanations

    sequences related to SQL database queries

    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
    202
    +0.15
    0.8%
    17
    +0.13
    0.7%
    481
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.15
    0.01
    37
    +0.13
    0.02
    481
    +0.12
    0.03
    Negative Logits
     reproduce
    -2.06
    ]{}]{}
    -1.74
     photoc
    -1.65
     safer
    -1.65
    ^[@
    -1.63
     suitable
    -1.61
    )^[@
    -1.58
    )\]
    -1.55
     technique
    -1.52
     techniques
    -1.52
    POSITIVE LOGITS
    Īĺ
    2.33
    ĻĤ
    2.02
    ı
    1.89
     nv
    1.80
    ľĵ
    1.74
    ples
    1.70
    ĭ
    1.70
     COUNT
    1.68
     LEFT
    1.65
    ¡
    1.65
    Activations Density 0.248%

    No Known Activations