© 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. 3795
    Prev
    Next
    INDEX
    Explanations

    mentions of financial transactions and economic policies

    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
    393
    +0.11
    0.6%
    685
    +0.11
    0.6%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.11
    0.10
    685
    +0.11
    0.03
    150
    +0.10
    0.07
    Negative Logits
    waters
    -0.66
    MODE
    -0.63
    çͰ
    -0.62
    SourceFile
    -0.60
    ocus
    -0.58
    utenberg
    -0.57
    âĵĺ
    -0.56
    JJ
    -0.55
    ONSORED
    -0.53
    mm
    -0.53
    POSITIVE LOGITS
     behalf
    1.31
    erous
    1.00
    yx
    0.89
    shore
    0.87
    site
    0.87
     sale
    0.81
    etime
    0.79
     arrival
    0.76
     average
    0.76
     weekends
    0.75
    Activations Density 7.234%

    No Known Activations