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. 28571
    Prev
    Next
    INDEX
    Explanations

    references to deposits and deposit-related concepts

    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
    142
    +0.12
    0.7%
    300
    +0.12
    0.7%
    177
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.12
    0.02
    128
    +0.12
    0.01
    300
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.37
    ¼
    -2.30
    ĩ
    -2.25
    ĸ´
    -2.24
    Ķ
    -2.09
    Īĺ
    -2.05
    ŀ
    -2.03
    ĭ
    -2.00
    £
    -1.99
    Į
    -1.95
    POSITIVE LOGITS
    recated
    1.70
    endant
    1.67
    ilation
    1.66
    onent
    1.65
    letion
    1.59
    th
    1.51
    leted
    1.50
    rived
    1.50
    raisal
    1.49
    raction
    1.47
    Activations Density 0.142%

    No Known Activations