© 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. 12027
    Prev
    Next
    INDEX
    Explanations

    forward-looking statements in financial documents, concerning potential future outcomes and risks

    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
    558
    +0.13
    0.5%
    311
    +0.12
    0.5%
    493
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.13
    0.01
    88
    +0.12
    0.01
    311
    +0.12
    0.01
    Negative Logits
    RGB
    -1.06
    inas
    -1.03
    ateurs
    -1.03
    neau
    -1.02
    ACP
    -1.00
    ulhu
    -0.99
    DERR
    -0.99
    >)
    -0.96
    aneous
    -0.94
    alos
    -0.94
    POSITIVE LOGITS
     relationships
    0.94
     Statements
    0.89
     relationship
    0.87
     Wik
    0.87
     covenant
    0.86
     directional
    0.81
     advisory
    0.81
     doctrine
    0.79
     Forth
    0.78
     conflict
    0.77
    Activations Density 0.029%

    No Known Activations