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. 29023
    Prev
    Next
    INDEX
    Explanations

    date and time-related information

    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
    422
    +0.13
    0.8%
    425
    +0.13
    0.7%
    207
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.13
    0.04
    163
    +0.13
    0.03
    21
    +0.12
    0.03
    Negative Logits
    ([]
    -1.57
    >(
    -1.48
    omy
    -1.40
     herein
    -1.38
     NCBI
    -1.37
    ?'
    -1.35
    [])
    -1.31
     therefrom
    -1.30
     bulky
    -1.26
    enance
    -1.26
    POSITIVE LOGITS
    ĥ½
    1.90
    ¾
    1.89
    ¤
    1.86
    Ŀ
    1.81
    ¿
    1.74
    Ĥ¬
    1.72
    ¡
    1.71
    ŀ
    1.70
    ¶
    1.65
     side
    1.64
    Activations Density 0.252%

    No Known Activations