© 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. 31503
    Prev
    Next
    INDEX
    Explanations

    phrases related to the journey or decisions made by individuals

    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
    98
    +0.15
    0.6%
    492
    +0.13
    0.5%
    494
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.15
    0.07
    107
    +0.13
    0.03
    314
    +0.12
    -0.08
    Negative Logits
    ãĤ´ãĥ³
    -1.01
     responsiveness
    -0.86
    CLASS
    -0.85
     heels
    -0.83
     envy
    -0.82
     orphans
    -0.78
    Ô
    -0.78
    INGTON
    -0.71
    wards
    -0.71
     vigorously
    -0.70
    POSITIVE LOGITS
    pora
    1.23
    nih
    1.09
    etus
    1.03
    cious
    0.94
    liction
    0.94
    arb
    0.91
    asio
    0.91
    ritical
    0.90
    incial
    0.89
     Deaths
    0.88
    Activations Density 11.007%

    No Known Activations