© 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 EvalsExportsinterp-engineNEWAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 31853
    Prev
    Next
    INDEX
    Explanations

    verbs related to achieving goals and targets

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.22
    0.9%
    173
    +0.12
    0.5%
    530
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.22
    0.05
    35
    +0.12
    0.07
    298
    +0.12
    0.09
    Negative Logits
     followed
    -0.75
     preceded
    -0.74
     ensued
    -0.72
     arose
    -0.71
     transpired
    -0.70
     survived
    -0.68
     sake
    -0.68
     endured
    -0.67
     expired
    -0.67
     descended
    -0.66
    POSITIVE LOGITS
     heights
    1.28
     milestone
    1.07
     milestones
    1.02
     pinnacle
    1.02
    levels
    0.99
     conclusion
    0.97
    reshold
    0.93
     halfway
    0.92
     plateau
    0.91
    iggurat
    0.91
    Activations Density 15.711%

    No Known Activations