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. 12013
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions

    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
    204
    +0.26
    1.5%
    302
    +0.14
    0.8%
    448
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.26
    0.18
    321
    +0.14
    0.08
    223
    +0.12
    0.05
    Negative Logits
    »¿
    -2.86
    ĥ½
    -2.48
    ħ
    -2.38
    Ĩ
    -2.36
    ģ
    -2.29
    Ŀ
    -2.26
    Ī
    -2.23
    ¡
    -2.22
    Ĥ¬
    -2.17
    ī
    -2.14
    POSITIVE LOGITS
    zza
    1.51
    cht
    1.38
     performs
    1.35
     functor
    1.27
    lied
    1.25
     reagent
    1.24
     withdrawing
    1.22
     contents
    1.22
    Äĩ
    1.22
     jug
    1.22
    Activations Density 6.759%

    No Known Activations