© 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
    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. 35096
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental policies and regulations

    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
    421
    +0.13
    0.5%
    316
    +0.12
    0.5%
    7
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.13
    0.09
    526
    +0.12
    -0.04
    25
    +0.11
    0.05
    Negative Logits
    perse
    -0.93
    hower
    -0.90
    ĪĴ
    -0.89
    isance
    -0.83
    cipl
    -0.82
    selves
    -0.81
    cause
    -0.79
    Reloaded
    -0.74
    æ©Ł
    -0.72
    issance
    -0.71
    POSITIVE LOGITS
    itol
    1.45
    aic
    1.19
    illary
    1.14
    itals
    0.99
    itated
    0.98
    stan
    0.96
    rice
    0.96
    aign
    0.94
    rison
    0.93
    uchin
    0.93
    Activations Density 4.871%

    No Known Activations