© 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. 40761
    Prev
    Next
    INDEX
    Explanations

    phrased related to international news and political developments

    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
    +0.27
    1.2%
    102
    +0.18
    0.8%
    640
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.27
    0.14
    160
    +0.18
    0.14
    314
    +0.15
    -0.02
    Negative Logits
     derby
    -0.84
     rul
    -0.82
     Story
    -0.77
     Versus
    -0.74
     Ross
    -0.73
     rall
    -0.72
    ĸļ
    -0.71
     blogging
    -0.71
     nodd
    -0.70
     rental
    -0.69
    POSITIVE LOGITS
    absolutely
    1.54
    extremely
    1.36
    probably
    1.32
    every
    1.30
    almost
    1.29
    very
    1.29
    completely
    1.28
    great
    1.27
    clear
    1.27
    really
    1.27
    Activations Density 8.144%

    No Known Activations