© 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. 33803
    Prev
    Next
    INDEX
    Explanations

    emotional content and sentiments in a narrative

    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
    132
    +0.13
    0.6%
    726
    +0.13
    0.6%
    393
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.13
    0.11
    132
    +0.13
    0.10
    393
    +0.12
    0.21
    Negative Logits
    xtap
    -0.89
    atan
    -0.76
    uca
    -0.74
    owe
    -0.71
    OCK
    -0.66
    imeter
    -0.65
    uckle
    -0.65
    Gra
    -0.64
     Classification
    -0.64
    ovie
    -0.64
    POSITIVE LOGITS
     importantly
    1.39
     than
    1.35
     ado
    0.97
     expensive
    0.97
     stringent
    0.95
     Than
    0.94
     sophisticated
    0.90
     efficient
    0.88
     likely
    0.88
     detailed
    0.86
    Activations Density 10.077%

    No Known Activations