© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28705
    Prev
    Next
    INDEX
    Explanations

    references to organizations and institutions involved in advocacy or legislative matters

    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
    457
    +0.15
    0.8%
    160
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.15
    0.06
    440
    +0.13
    0.05
    160
    +0.12
    0.05
    Negative Logits
    mann
    -1.64
    imer
    -1.50
    icular
    -1.49
     access
    -1.48
     sense
    -1.44
     indication
    -1.44
    InstanceState
    -1.41
    chart
    -1.40
    ier
    -1.38
     limit
    -1.38
    POSITIVE LOGITS
    IJ
    4.40
    ¿½
    4.39
    ľĵ
    4.36
    »¿
    4.25
    ½
    4.22
    ↵
    4.21
    <|outofrange|>
    4.21
     ↵
    4.21
    <|outofrange|>
    4.21
    ↵  âĢĥ
    4.21
    Activations Density 0.370%

    No Known Activations