© 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. 4850
    Prev
    Next
    INDEX
    Explanations

    acronyms or proper names related to news agencies or technology entities

    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
    270
    +0.15
    0.6%
    447
    +0.14
    0.5%
    659
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.15
    0.06
    339
    +0.14
    0.06
    659
    +0.13
    0.07
    Negative Logits
    terday
    -0.81
     thumbs
    -0.80
     capitalist
    -0.79
    wagen
    -0.78
    Reloaded
    -0.77
     afore
    -0.75
     Jenner
    -0.75
     trout
    -0.74
     stabil
    -0.74
     Ridley
    -0.72
    POSITIVE LOGITS
    PLIED
    1.43
    PLE
    1.42
    PLIC
    1.35
    sburg
    1.21
    PRO
    1.19
    PROV
    1.19
    PL
    1.19
    PAR
    1.18
    PLA
    1.17
    OE
    1.17
    Activations Density 6.389%

    No Known Activations