© 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. 3299
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "with or without" appears

    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
    147
    +0.14
    0.5%
    649
    +0.13
    0.5%
    393
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.14
    0.08
    278
    +0.13
    0.07
    225
    +0.12
    0.07
    Negative Logits
    achine
    -1.00
    auga
    -0.98
     Pony
    -0.91
    efer
    -0.84
    istors
    -0.79
    ocrat
    -0.78
    ascus
    -0.77
     Dragonbound
    -0.77
     Parables
    -0.75
    elong
    -0.75
    POSITIVE LOGITS
    nery
    1.69
    chard
    1.63
    Else
    1.61
    acles
    1.55
    ifice
    1.53
    acle
    1.43
    nam
    1.34
    chid
    1.32
    leans
    1.29
    acular
    1.25
    Activations Density 1.202%

    No Known Activations