© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30597
    Prev
    Next
    INDEX
    Explanations

    a variety of emotional expressions and responses

    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
    302
    +0.15
    0.9%
    12
    +0.14
    0.8%
    261
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.15
    0.10
    504
    +0.14
    0.05
    322
    +0.12
    -0.00
    Negative Logits
    ------
    -1.90
    cerning
    -1.61
    --
    -1.59
    ~~~
    -1.56
    onectin
    -1.52
    ruvate
    -1.52
    ----
    -1.51
    gets
    -1.44
    ploy
    -1.41
    ently
    -1.40
    POSITIVE LOGITS
     indications
    1.39
    ĥ½
    1.26
     vess
    1.25
    »¿
    1.23
    ]))
    1.23
    dtd
    1.23
    ±
    1.22
    },\\
    1.22
     shores
    1.22
    }\\
    1.21
    Activations Density 3.314%

    No Known Activations