© 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. 6539
    Prev
    Next
    INDEX
    Explanations

    terms related to remote control or management, especially in the context of technological systems and operations

    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
    288
    +0.28
    1.0%
    238
    +0.15
    0.6%
    362
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.09
    302
    +0.15
    0.05
    99
    +0.15
    0.04
    Negative Logits
    OIL
    -1.14
    ICAN
    -1.10
    utenberg
    -1.04
    hetti
    -1.00
    VERTISEMENT
    -1.00
    ÏĦ
    -0.98
    gans
    -0.96
    ione
    -0.96
    в
    -0.95
    iris
    -0.94
    POSITIVE LOGITS
     sensing
    1.17
    sighted
    0.98
    bole
    0.98
     detachment
    0.93
     controlled
    0.92
    etheless
    0.92
     remote
    0.91
    pathic
    0.91
     peripher
    0.90
    visor
    0.89
    Activations Density 0.936%

    No Known Activations