© 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 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. 33253
    Prev
    Next
    INDEX
    Explanations

    texts discussing the directionality of time, focusing on concepts related to moving backwards or forwards in time

    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
    288
    +0.15
    0.7%
    447
    +0.11
    0.5%
    316
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.15
    0.05
    288
    +0.11
    0.14
    714
    +0.10
    0.04
    Negative Logits
    ateurs
    -0.82
    raltar
    -0.81
    rament
    -0.81
    oleon
    -0.77
    abase
    -0.74
    anooga
    -0.74
    lez
    -0.74
    riz
    -0.73
    rol
    -0.72
    atum
    -0.72
    POSITIVE LOGITS
    wards
    0.92
    stairs
    0.87
    ward
    0.87
     compatibility
    0.84
     compat
    0.78
     spiral
    0.78
    WARD
    0.77
    step
    0.74
    side
    0.72
     reflection
    0.66
    Activations Density 5.090%

    No Known Activations