© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32767
    Prev
    Next
    INDEX
    Explanations

    academic references and data related to global trade and resource imports/exports

    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
    +0.25
    1.0%
    545
    +0.12
    0.5%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.26
    336
    +0.12
    0.06
    2
    +0.11
    0.03
    Negative Logits
     advoc
    -0.77
     rug
    -0.70
     cov
    -0.70
     solicitor
    -0.69
     TF
    -0.67
    oters
    -0.67
    okes
    -0.65
    ELF
    -0.65
     Loot
    -0.64
     PROG
    -0.64
    POSITIVE LOGITS
    2008
    1.28
    2001
    1.27
    2006
    1.26
     2010
    1.26
     1995
    1.26
     2006
    1.26
    2010
    1.26
    1992
    1.25
     2008
    1.24
    2011
    1.24
    Activations Density 10.486%

    No Known Activations