© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36578
    Prev
    Next
    INDEX
    Explanations

    terms related to transportation and vehicles, specifically focusing on airplane terminology and car parts

    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
    218
    +0.07
    0.5%
    288
    +0.06
    0.5%
    216
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.07
    0.21
    575
    +0.06
    0.14
    326
    +0.06
    0.20
    Negative Logits
    inos
    -0.46
    ovsky
    -0.45
    Torrent
    -0.44
    ggies
    -0.43
     Berks
    -0.43
    UGC
    -0.41
    inator
    -0.40
    oshenko
    -0.40
    idi
    -0.39
    о
    -0.39
    POSITIVE LOGITS
     compartment
    0.62
     cockpit
    0.53
     cabin
    0.53
     liner
    0.49
    lain
    0.48
    artment
    0.48
     drawer
    0.47
     doors
    0.46
     suites
    0.45
    etry
    0.45
    Activations Density 7.035%

    No Known Activations