© 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 Local
    9. 6-RES_SCL-AJT
    11. 34780
    Prev
    Next
    INDEX
    Explanations

    phrases related to aviation and energy

    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
    60
    +0.03
    0.5%
    31
    +0.03
    0.5%
    288
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.03
    0.27
    267
    +0.03
    0.12
    145
    +0.03
    0.08
    Negative Logits
    onto
    -0.20
    tal
    -0.20
    hood
    -0.19
     Shutterstock
    -0.17
     rob
    -0.17
    hov
    -0.17
    reads
    -0.17
    ta
    -0.17
    ÃĹ
    -0.17
    mount
    -0.16
    POSITIVE LOGITS
     Authority
    0.29
     Administration
    0.26
     Regulations
    0.25
     Department
    0.24
     Facilities
    0.24
     Federation
    0.24
     Zone
    0.23
     System
    0.23
     Inspect
    0.23
     Facility
    0.22
    Activations Density 13.368%

    No Known Activations