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. 12025
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    298
    +0.12
    0.7%
    174
    +0.12
    0.6%
    96
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.12
    0.00
    1
    -0.12
    0.00
    2
    -0.11
    0.00
    Negative Logits
    []
    -1.66
    ]);
    -1.45
    umerable
    -1.45
     intervals
    -1.44
    )"
    -1.39
     defaults
    -1.38
    ]",
    -1.38
     farewell
    -1.37
    onymous
    -1.36
    [,
    -1.35
    POSITIVE LOGITS
    antine
    1.52
    iang
    1.51
    rends
    1.48
    cknowled
    1.48
    yz
    1.47
     Department
    1.41
    tering
    1.40
    oretic
    1.39
    STIT
    1.37
    »
    1.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.