© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26388
    Prev
    Next
    INDEX
    Explanations

    quotes or phrases indicating the significance of students and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    145
    +0.14
    0.8%
    425
    +0.13
    0.7%
    121
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.14
    0.06
    103
    +0.13
    0.05
    461
    +0.13
    0.05
    Negative Logits
     news
    -1.54
     these
    -1.45
    taient
    -1.44
     holidays
    -1.43
    ÑģÑĤва
    -1.41
     newspaper
    -1.41
    nier
    -1.40
    tered
    -1.35
    lies
    -1.35
    avirus
    -1.33
    POSITIVE LOGITS
    ĥ½
    2.71
    ¹
    2.70
    IJ
    2.55
    Ļ
    2.52
    ·¸
    2.50
    ¤
    2.28
    °
    2.21
    ¿½
    2.18
    ħ
    2.17
    Ķ
    2.16
    Activations Density 0.252%

    No Known Activations