© 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. 14328
    Prev
    Next
    INDEX
    Explanations

    the verbs related to taking action or exerting force on something

    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
    526
    +0.18
    0.6%
    636
    +0.18
    0.6%
    393
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.18
    0.07
    526
    +0.18
    0.00
    362
    +0.17
    0.06
    Negative Logits
    lia
    -1.05
    SEA
    -1.01
    ################################
    -1.00
    MAL
    -0.99
    ENN
    -0.95
    outheastern
    -0.94
    swick
    -0.92
    APH
    -0.92
    nces
    -0.91
     Letters
    -0.91
    POSITIVE LOGITS
     harder
    1.38
     hardest
    1.20
     curtain
    1.15
     pedal
    1.13
     envelope
    1.10
     hard
    1.09
     sticks
    1.07
     wedge
    1.07
     stick
    1.04
     knees
    0.99
    Activations Density 1.379%

    No Known Activations