© 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. 3213
    Prev
    Next
    INDEX
    Explanations

    phrases related to natural resources and resource management

    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
    +0.25
    1.0%
    653
    +0.18
    0.7%
    150
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.25
    0.07
    653
    +0.18
    0.05
    225
    +0.13
    0.05
    Negative Logits
    arella
    -1.09
    alone
    -1.03
    ouk
    -0.92
    ker
    -0.87
    ŃĶ
    -0.85
    lihood
    -0.85
    bone
    -0.85
    redd
    -0.85
    rooms
    -0.82
    ership
    -0.81
    POSITIVE LOGITS
     resources
    1.16
    fulness
    0.96
    utical
    0.95
    folios
    0.91
     management
    0.90
     Resources
    0.89
     allocation
    0.89
    available
    0.86
    iture
    0.84
     Pwr
    0.84
    Activations Density 0.744%

    No Known Activations