© 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. 45948
    Prev
    Next
    INDEX
    Explanations

    charitable activities, organizations, and donations

    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
    +0.17
    0.9%
    288
    +0.17
    0.9%
    71
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.17
    0.08
    608
    +0.17
    0.15
    197
    +0.11
    0.08
    Negative Logits
    anian
    -0.67
    amura
    -0.65
     Zheng
    -0.60
    Phones
    -0.59
    ymes
    -0.57
     Demand
    -0.56
     Awakening
    -0.56
    gran
    -0.56
     Rasmussen
    -0.55
     Wizard
    -0.55
    POSITIVE LOGITS
     charity
    0.80
     charities
    0.77
     fundraising
    0.76
     fundra
    0.75
     donation
    0.70
     laureate
    0.66
     fundraiser
    0.65
     stripe
    0.64
     charitable
    0.64
     donate
    0.63
    Activations Density 9.214%

    No Known Activations