© 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. 5613
    Prev
    Next
    INDEX
    Explanations

    phrases related to attitudes and perspectives

    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
    195
    +0.14
    0.6%
    288
    +0.14
    0.5%
    575
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.15
    247
    +0.14
    0.09
    575
    +0.13
    0.12
    Negative Logits
    icles
    -1.07
    enegger
    -1.00
    icle
    -0.90
    idden
    -0.87
    ographers
    -0.87
    ÄŁ
    -0.85
    rake
    -0.80
    oval
    -0.79
    pedia
    -0.79
    eri
    -0.79
    POSITIVE LOGITS
     toward
    1.19
     towards
    1.16
     attitude
    1.15
    uation
    1.02
     attitudes
    0.98
     Towards
    0.90
     disposition
    0.90
    uated
    0.89
    ysis
    0.87
     attachment
    0.86
    Activations Density 2.538%

    No Known Activations