© 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. 35226
    Prev
    Next
    INDEX
    Explanations

    technical programming-related terms and code snippets

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.24
    3.2%
    64
    +0.16
    2.1%
    481
    +0.14
    1.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.24
    -0.11
    64
    +0.16
    -0.33
    283
    +0.14
    0.03
    Negative Logits
     âĢº
    -0.20
    epad
    -0.17
    Origin
    -0.17
     NBN
    -0.17
    Picture
    -0.17
    Brexit
    -0.17
     spoilers
    -0.17
     TMZ
    -0.17
    OIL
    -0.16
    usterity
    -0.16
    POSITIVE LOGITS
    anwhile
    0.34
    ]."
    0.25
    ]).
    0.25
    ogether
    0.24
    "/>
    0.24
     };
    0.24
     respectively
    0.23
    }.
    0.23
    .).
    0.22
     millenn
    0.22
    Activations Density 20.540%

    No Known Activations