© 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. 757
    Prev
    Next
    INDEX
    Explanations

    information related to news articles involving law enforcement and criminal activities

    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
    679
    +0.26
    0.8%
    441
    +0.16
    0.5%
    283
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.26
    0.07
    274
    +0.16
    0.08
    441
    +0.14
    0.07
    Negative Logits
    ptives
    -1.04
     ILCS
    -1.02
    ï¸
    -1.01
    ez
    -1.00
    pel
    -1.00
    Desktop
    -0.98
    anu
    -0.97
    otin
    -0.97
    wed
    -0.96
    ption
    -0.94
    POSITIVE LOGITS
    doms
    1.27
     goodbye
    1.12
     inspector
    0.91
     strings
    0.89
     investigators
    0.88
     seq
    0.87
     sources
    0.86
     earlier
    0.86
     declass
    0.85
     dism
    0.83
    Activations Density 0.762%

    No Known Activations