© 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. 32777
    Prev
    Next
    INDEX
    Explanations

    terms related to geopolitical events, individuals, and locations

    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
    709
    +0.15
    0.5%
    286
    +0.14
    0.5%
    383
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.17
    767
    +0.14
    0.08
    526
    +0.14
    -0.04
    Negative Logits
     Lauder
    -0.89
     ESA
    -0.85
     Oblivion
    -0.82
     readable
    -0.81
     hect
    -0.79
    FTWARE
    -0.79
     irrad
    -0.78
    ufact
    -0.78
     mammals
    -0.77
    OGR
    -0.77
    POSITIVE LOGITS
    iu
    1.24
    iao
    1.23
    dn
    1.23
    edo
    1.21
    aeda
    1.19
    eus
    1.16
    rt
    1.15
    lling
    1.15
    agan
    1.14
    arth
    1.13
    Activations Density 6.517%

    No Known Activations