© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5606
    Prev
    Next
    INDEX
    Explanations

    phrases related to commerce, promotions, and discount offers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.14
    0.5%
    640
    +0.13
    0.5%
    25
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.14
    0.06
    314
    +0.13
    -0.00
    160
    +0.13
    0.10
    Negative Logits
    ouple
    -0.86
    ÄŁ
    -0.86
    ority
    -0.85
     leaps
    -0.84
     pauses
    -0.82
     roam
    -0.81
    ressing
    -0.80
     intimidated
    -0.78
     Brune
    -0.78
     simultane
    -0.78
    POSITIVE LOGITS
    ACTED
    1.07
    VAL
    0.97
    XXX
    0.91
    2020
    0.90
    CV
    0.90
     "#
    0.90
    DX
    0.89
     Pwr
    0.88
    XX
    0.88
    XY
    0.85
    Activations Density 1.789%

    No Known Activations