© 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. 32843
    Prev
    Next
    INDEX
    Explanations

    words related to tests and evaluations

    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
    +0.14
    0.7%
    386
    +0.12
    0.6%
    328
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.10
    561
    +0.12
    0.08
    358
    +0.12
    0.06
    Negative Logits
    EngineDebug
    -0.76
    etheless
    -0.76
    vironment
    -0.73
    cedented
    -0.70
     coh
    -0.67
    coal
    -0.67
     Leilan
    -0.65
    resent
    -0.65
    ovie
    -0.64
     Hort
    -0.63
    POSITIVE LOGITS
    osterone
    1.25
    imony
    0.96
    icles
    0.91
    ysis
    0.86
    icular
    0.84
    ifies
    0.84
    icle
    0.79
    imon
    0.79
    ifiers
    0.77
    udo
    0.75
    Activations Density 8.446%

    No Known Activations