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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 40936
    Prev
    Next
    INDEX
    Explanations

    phrases related to mental health disorders, particularly focusing on depression

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.26
    1.2%
    288
    +0.18
    0.8%
    508
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.26
    0.17
    151
    +0.18
    0.12
    132
    +0.11
    0.06
    Negative Logits
    Reply
    -0.82
    Sources
    -0.81
    SPONSORED
    -0.81
    seeing
    -0.80
    tnc
    -0.78
    leigh
    -0.77
    aque
    -0.76
    lay
    -0.75
    icles
    -0.73
    Grab
    -0.72
    POSITIVE LOGITS
     relapse
    0.93
     depression
    0.93
     depressive
    0.85
     symptoms
    0.80
     distress
    0.78
     depress
    0.75
     Mood
    0.75
     diagnosis
    0.73
     worsen
    0.72
     mell
    0.71
    Activations Density 6.343%

    No Known Activations