© 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. 40555
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking direct or proactive action instead of waiting passively

    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
    +0.12
    0.6%
    134
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.24
    283
    +0.10
    -0.00
    593
    +0.10
    0.06
    Negative Logits
    ģ«
    -0.68
     endeavour
    -0.64
    catentry
    -0.64
    Ĥİ
    -0.63
    erenn
    -0.59
    £ı
    -0.55
     endeavor
    -0.55
     locality
    -0.54
    ranged
    -0.54
    qua
    -0.53
    POSITIVE LOGITS
     idle
    0.70
    agra
    0.68
     drawer
    0.67
    oin
    0.64
    rolled
    0.63
    ACTED
    0.63
    ulhu
    0.62
    isode
    0.61
     pedest
    0.61
     benches
    0.60
    Activations Density 11.100%

    No Known Activations