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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11679
    Prev
    Next
    INDEX
    Explanations

    discussions around the complexity of identity and relationships

    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
    186
    +0.38
    2.3%
    207
    +0.13
    0.8%
    451
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.38
    0.13
    451
    +0.13
    0.03
    270
    +0.12
    0.08
    Negative Logits
    >::
    -1.51
    >();
    -1.49
     reasonableness
    -1.38
     varchar
    -1.37
     testimony
    -1.36
     incoming
    -1.32
     quoted
    -1.32
     validity
    -1.31
    };
    -1.30
     latest
    -1.27
    POSITIVE LOGITS
    oler
    1.56
    olate
    1.53
    erty
    1.52
    cler
    1.51
    hips
    1.46
    kill
    1.44
    landers
    1.42
     \[[
    1.41
    bos
    1.36
    [-
    1.36
    Activations Density 4.531%

    No Known Activations