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. 11873
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references

    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
    153
    +0.23
    1.4%
    271
    +0.14
    0.9%
    17
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.23
    0.09
    210
    +0.14
    0.03
    271
    +0.13
    -0.01
    Negative Logits
    éric
    -1.60
    aceut
    -1.47
     duty
    -1.42
    othermal
    -1.41
     legally
    -1.38
     counseling
    -1.36
    ologically
    -1.36
    odox
    -1.35
    braska
    -1.32
    iably
    -1.32
    POSITIVE LOGITS
    ľĵ
    3.29
    ĻĤ
    3.00
    ½
    2.97
    ²
    2.96
    Ļ
    2.75
    ĨĴ
    2.68
    »
    2.66
    ©
    2.62
    č↵č↵           
    2.60
                                                                                  
    2.60
    Activations Density 2.052%

    No Known Activations