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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11936
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I" indicating personal statements or experiences

    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
    478
    +0.17
    1.0%
    410
    +0.15
    0.8%
    81
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.17
    0.04
    81
    +0.15
    0.05
    410
    +0.12
    0.06
    Negative Logits
    ŀ
    -2.12
    ¬
    -2.01
    ĻĤ
    -1.99
    ł
    -1.91
    °
    -1.90
    ľĵ
    -1.86
    Ħ
    -1.85
    «
    -1.82
    ¿½
    -1.82
    »¿
    -1.77
    POSITIVE LOGITS
    reland
    2.46
    celand
    2.46
    stanbul
    2.30
    nex
    2.26
     wonder
    2.19
    NdEx
    2.00
     guess
    1.97
    'm
    1.96
     suppose
    1.95
    rene
    1.89
    Activations Density 0.140%

    No Known Activations