© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12984
    Prev
    Next
    INDEX
    Explanations

    descriptions related to various events or occurrences

    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
    446
    +0.15
    0.5%
    673
    +0.15
    0.5%
    151
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.15
    673
    +0.15
    0.09
    363
    +0.14
    0.07
    Negative Logits
     oneself
    -0.89
     Tud
    -0.81
     Guan
    -0.81
    someone
    -0.80
     Topic
    -0.79
    dating
    -0.79
     Bett
    -0.79
     Saban
    -0.78
    theless
    -0.77
    KING
    -0.76
    POSITIVE LOGITS
     spree
    1.00
     woes
    0.97
     selves
    0.96
     rampage
    0.94
     counterparts
    0.89
    ottest
    0.87
    âĺ
    0.86
    ãĥķãĤ©
    0.86
    iour
    0.84
     cousins
    0.84
    Activations Density 3.384%

    No Known Activations