© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 3804
    Prev
    Next
    INDEX
    Explanations

    references to financial numbers and monetary transactions

    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
    +0.14
    0.6%
    314
    +0.13
    0.6%
    578
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.14
    0.06
    443
    +0.13
    0.05
    344
    +0.13
    0.09
    Negative Logits
     Gors
    -0.94
     exerc
    -0.92
     constitu
    -0.85
     Sed
    -0.84
     Halls
    -0.80
     Tid
    -0.79
     Stru
    -0.78
     Slov
    -0.76
     partName
    -0.76
     Bre
    -0.75
    POSITIVE LOGITS
    $$
    1.25
    $$$$
    1.10
     Donation
    1.07
    USD
    1.06
    -$
    0.97
    100
    0.96
    500
    0.93
    ($
    0.93
    dollar
    0.92
    250
    0.91
    Activations Density 5.055%

    No Known Activations