© 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 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 Local
    9. 6-RES_SCL-AJT
    11. 33597
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical injuries or medical conditions in the upper body

    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
    71
    +0.04
    0.5%
    79
    +0.04
    0.5%
    515
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.04
    -0.02
    48
    +0.04
    0.11
    9
    +0.03
    0.12
    Negative Logits
     Parenthood
    -0.25
     Bacon
    -0.22
     BET
    -0.22
     Term
    -0.22
    esson
    -0.22
     CBI
    -0.22
     Amendments
    -0.22
     Bunny
    -0.22
     Monthly
    -0.21
     Monsanto
    -0.21
    POSITIVE LOGITS
    plane
    0.27
    hari
    0.27
    wash
    0.26
    hair
    0.25
    butt
    0.25
     circumference
    0.24
     agility
    0.24
    shake
    0.24
    jah
    0.24
    Phys
    0.24
    Activations Density 13.055%

    No Known Activations