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. 29074
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and institutions

    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
    419
    +0.28
    1.7%
    12
    +0.21
    1.3%
    161
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.28
    0.13
    136
    +0.21
    -0.06
    12
    +0.14
    0.15
    Negative Logits
     catalogue
    -1.64
    cknowled
    -1.63
    º
    -1.61
    Ļª
    -1.60
    Ĵ
    -1.60
    ª
    -1.53
                             
    -1.50
    <|outofrange|>
    -1.50
    ↵             
    -1.50
              
    -1.50
    POSITIVE LOGITS
    ,'"
    1.73
    .'"
    1.73
    ]'
    1.72
    "}](#
    1.49
    experienced
    1.48
     ;;
    1.46
     ];
    1.43
    ,'
    1.43
     necessarily
    1.40
     }(
    1.40
    Activations Density 4.655%

    No Known Activations