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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5517
    Prev
    Next
    INDEX
    Explanations

    phrases related to future events or actions

    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
    339
    +0.17
    0.6%
    393
    +0.16
    0.5%
    105
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.17
    0.07
    718
    +0.16
    0.06
    339
    +0.16
    0.05
    Negative Logits
     Parables
    -0.93
    didn
    -0.93
     Howe
    -0.92
     Compass
    -0.87
     Hemisphere
    -0.87
    croft
    -0.86
     memes
    -0.84
     gateway
    -0.83
     Monte
    -0.82
    quickShipAvailable
    -0.82
    POSITIVE LOGITS
     embark
    1.49
    pload
    1.32
    NetMessage
    1.30
     expire
    1.24
     retire
    1.24
     arrive
    1.18
     settle
    1.18
     unleash
    1.17
     replace
    1.16
     explode
    1.15
    Activations Density 0.609%

    No Known Activations