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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27021
    Prev
    Next
    INDEX
    Explanations

    the preposition "from" 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__res-sm_processed/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    69
    +0.13
    0.7%
    85
    +0.13
    0.7%
    326
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.04
    493
    +0.13
    0.02
    62
    +0.11
    0.02
    Negative Logits
     increment
    -1.54
     cycle
    -1.47
     pause
    -1.46
     meter
    -1.43
     embargo
    -1.39
    stro
    -1.38
     decis
    -1.34
     tempo
    -1.34
    -->
    -1.34
     spins
    -1.33
    POSITIVE LOGITS
    oxin
    1.84
    ©
    1.79
    affin
    1.71
    apine
    1.67
    uk
    1.65
    ondon
    1.64
    ĻĤ
    1.64
    quette
    1.61
    tgz
    1.60
    nj
    1.56
    Activations Density 0.161%

    No Known Activations