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

    Neuronpedia

    APICircuit 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. 11589
    Prev
    Next
    INDEX
    Explanations

    user interface terms and elements related to UI design

    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
    12
    +0.13
    0.7%
    122
    +0.12
    0.7%
    24
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.13
    0.07
    188
    +0.12
    0.01
    78
    +0.12
    0.04
    Negative Logits
    Ĺ
    -2.52
    ©
    -2.46
    ¤
    -2.34
    ľĵ
    -2.33
    §
    -2.27
    Ī
    -2.27
    ļ
    -2.24
    ´
    -2.24
    Ļ
    -2.19
    ĸ
    -2.17
    POSITIVE LOGITS
     Contest
    1.43
     Armed
    1.37
     Encyclopedia
    1.36
    ]"
    1.36
    rea
    1.32
    ]:
    1.30
     Problem
    1.28
     anthem
    1.28
    ]."
    1.26
    conspir
    1.25
    Activations Density 3.875%

    No Known Activations