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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12485
    Prev
    Next
    INDEX
    Explanations

    financial and economic themes or words related to money

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    451
    +0.12
    0.5%
    496
    +0.12
    0.4%
    493
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.27
    575
    +0.12
    0.18
    35
    +0.11
    0.10
    Negative Logits
     Adin
    -0.76
    aque
    -0.75
    ference
    -0.75
    osen
    -0.75
    ARB
    -0.75
     Width
    -0.75
    Flag
    -0.74
    ENDED
    -0.74
     Fra
    -0.73
    inct
    -0.72
    POSITIVE LOGITS
     lucrative
    0.99
     bribes
    0.93
     profits
    0.93
     sponsorship
    0.92
     receipts
    0.92
    umed
    0.91
     money
    0.90
     mogul
    0.89
    iless
    0.88
     profit
    0.88
    Activations Density 5.714%

    No Known Activations