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. 28940
    Prev
    Next
    INDEX
    Explanations

    words related to specific identities or classifications

    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
    419
    +0.28
    1.6%
    121
    +0.16
    0.9%
    479
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.28
    0.09
    134
    +0.16
    0.07
    66
    +0.15
    0.07
    Negative Logits
    noreply
    -1.59
     heartbeat
    -1.49
     saf
    -1.42
    roit
    -1.36
     Proced
    -1.27
     probable
    -1.25
     Fourth
    -1.24
    },\\
    -1.23
    amac
    -1.22
     nearby
    -1.22
    POSITIVE LOGITS
     talks
    1.71
    uler
    1.61
     negotiations
    1.54
     discussions
    1.49
    ondo
    1.49
     apart
    1.43
    inking
    1.43
    anian
    1.42
    gard
    1.39
    uled
    1.38
    Activations Density 0.538%

    No Known Activations