© 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. 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. 31652
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and expressions related to emotional reactions

    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
    +0.22
    1.0%
    204
    +0.12
    0.5%
    736
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    702
    +0.22
    0.11
    492
    +0.12
    0.06
    690
    +0.10
    0.06
    Negative Logits
     Caption
    -0.74
     grievances
    -0.71
     surn
    -0.70
    >[
    -0.68
     surname
    -0.64
     relinqu
    -0.63
     vacated
    -0.60
     Partial
    -0.60
    ida
    -0.60
     coun
    -0.59
    POSITIVE LOGITS
    ciating
    1.16
     unbeliev
    1.03
     phenomenal
    0.93
     pandemonium
    0.93
     incredible
    0.92
     amazing
    0.90
     unbelievable
    0.90
     Awesome
    0.88
    !!!!!
    0.85
    Wow
    0.85
    Activations Density 25.191%

    No Known Activations