© 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. 31602
    Prev
    Next
    INDEX
    Explanations

    quotes or reported statements in a formal or technical context

    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
    +0.24
    1.0%
    167
    +0.14
    0.6%
    311
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.24
    0.07
    330
    +0.14
    0.09
    659
    +0.13
    0.10
    Negative Logits
    vier
    -0.85
     Aether
    -0.78
     Miko
    -0.77
     Twain
    -0.76
     mater
    -0.74
     Clever
    -0.74
     Boone
    -0.74
     Hole
    -0.73
     Conquest
    -0.73
     Hades
    -0.73
    POSITIVE LOGITS
    ortun
    1.51
    ocused
    1.46
    ruits
    1.45
    ortunate
    1.43
    ocusing
    1.42
    avour
    1.39
    ertility
    1.36
    reet
    1.34
    raction
    1.33
    OUND
    1.33
    Activations Density 8.454%

    No Known Activations