© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal development and growth

    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
    216
    +0.19
    0.7%
    447
    +0.18
    0.7%
    670
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.19
    0.32
    447
    +0.18
    0.33
    64
    +0.14
    -0.14
    Negative Logits
    oute
    -0.98
    phis
    -0.96
    ioned
    -0.90
    ãĥīãĥ©
    -0.90
    esson
    -0.86
    arted
    -0.81
    pta
    -0.78
    perse
    -0.78
    rolled
    -0.77
    PLIC
    -0.76
    POSITIVE LOGITS
     exponentially
    1.08
     promot
    1.07
     pains
    0.97
     accustomed
    0.85
     stronger
    0.85
    aroo
    0.85
     explos
    0.85
    nir
    0.81
    ls
    0.80
    ollen
    0.80
    Activations Density 7.119%

    No Known Activations