© 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. 5726
    Prev
    Next
    INDEX
    Explanations

    various prompts related to subscribing, supporting, and taking action on a particular platform or program

    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
    197
    +0.12
    0.5%
    311
    +0.12
    0.5%
    340
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.12
    0.03
    97
    +0.12
    0.03
    313
    +0.11
    0.03
    Negative Logits
    terday
    -1.02
    osuke
    -0.96
    ikan
    -0.88
    hower
    -0.82
    earch
    -0.81
     prophes
    -0.79
     ende
    -0.78
    upon
    -0.78
    âĢİ
    -0.76
    ilts
    -0.76
    POSITIVE LOGITS
     Latest
    0.90
     Crowd
    0.88
     Campaign
    0.87
     Hits
    0.84
     Above
    0.83
     Partnership
    0.83
     Board
    0.82
     Simulator
    0.82
    Ability
    0.82
     Survive
    0.82
    Activations Density 0.177%

    No Known Activations