© 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. 39891
    Prev
    Next
    INDEX
    Explanations

    numeric information or descriptions, such as prices, measurements, quantities, or dates

    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
    +0.21
    1.1%
    481
    +0.19
    1.0%
    393
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.20
    362
    +0.19
    0.13
    608
    +0.15
    0.15
    Negative Logits
    amiya
    -0.72
    flix
    -0.65
    sson
    -0.64
    amed
    -0.63
     Unsure
    -0.63
    ghan
    -0.62
    Quantity
    -0.60
    event
    -0.60
    aly
    -0.59
     Controls
    -0.58
    POSITIVE LOGITS
     own
    0.97
     namesake
    0.87
     newest
    0.81
    ELF
    0.75
     predecessor
    0.71
     maiden
    0.70
     signature
    0.70
     inability
    0.70
     longevity
    0.70
     demise
    0.70
    Activations Density 7.595%

    No Known Activations