© 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. 40742
    Prev
    Next
    INDEX
    Explanations

    comparative statements indicating a higher degree of a certain quality or characteristic

    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
    +0.13
    0.6%
    393
    +0.13
    0.5%
    647
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.13
    0.21
    55
    +0.13
    0.17
    512
    +0.12
    0.10
    Negative Logits
    xtap
    -0.85
    etimes
    -0.81
    æ©
    -0.78
    atan
    -0.77
    pex
    -0.77
    utions
    -0.75
    ovies
    -0.74
    heid
    -0.71
    rosis
    -0.70
    ividual
    -0.68
    POSITIVE LOGITS
     than
    1.44
     likely
    1.13
     efficient
    1.13
     accurate
    1.12
     important
    1.06
     complicated
    1.06
     expensive
    1.01
     inclined
    1.01
     sophisticated
    1.00
     importantly
    1.00
    Activations Density 7.201%

    No Known Activations