© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12420
    Prev
    Next
    INDEX
    Explanations

    conversations about mental health and self-perception

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •probe features
    promotes she/her

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    398
    +0.13
    0.7%
    20
    +0.13
    0.7%
    306
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.13
    0.02
    20
    +0.13
    0.19
    56
    +0.11
    0.05
    Negative Logits
     */
    -2.78
    */
    -2.75
    \]-
    -2.35
     */,
    -2.33
    \]\].
    -2.29
    \].
    -2.27
    **).
    -2.25
    \];
    -2.21
    **:
    -2.16
    ?**
    -2.13
    POSITIVE LOGITS
     her
    7.11
     she
    6.64
     herself
    6.16
     She
    5.18
     hers
    5.16
    she
    4.61
     Her
    4.55
    She
    4.51
    Her
    3.90
    her
    3.58
    Activations Density 7.889%

    No Known Activations