© 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. 33901
    Prev
    Next
    INDEX
    Explanations

    keywords related to political and economic topics

    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
    352
    +0.14
    0.6%
    575
    +0.12
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.14
    0.32
    352
    +0.12
    0.30
    23
    +0.11
    0.28
    Negative Logits
     Bunny
    -0.77
     unmarked
    -0.74
    creen
    -0.74
     vom
    -0.72
     gib
    -0.71
     Yon
    -0.67
     scattering
    -0.67
     reception
    -0.65
     compiling
    -0.64
     Zucker
    -0.63
    POSITIVE LOGITS
    requires
    0.98
    ¬
    0.95
    agree
    0.95
    order
    0.94
    ¹
    0.92
    elong
    0.91
    0.86
    âĢł
    0.84
    immer
    0.84
    since
    0.83
    Activations Density 7.036%

    No Known Activations