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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26758
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their roles in various contexts

    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
    85
    +0.16
    0.9%
    464
    +0.13
    0.7%
    337
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.16
    0.06
    135
    +0.13
    0.08
    170
    +0.11
    0.09
    Negative Logits
    :`
    -1.75
    ancellor
    -1.55
    asone
    -1.55
    ISPR
    -1.52
    igi
    -1.47
    iator
    -1.41
    :--
    -1.41
    AFP
    -1.40
    ADVERTISEMENT
    -1.39
    @"
    -1.38
    POSITIVE LOGITS
    IJ
    2.04
    ¡
    1.80
     tears
    1.68
    Ĺ
    1.66
    holds
    1.66
     jeans
    1.56
     bathrooms
    1.54
     stairs
    1.53
     cis
    1.50
     baths
    1.45
    Activations Density 3.824%

    No Known Activations