© 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 Local
    9. 6-RES_SCL-AJT
    11. 33668
    Prev
    Next
    INDEX
    Explanations

    words related to leaving a job or situation

    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
    +0.21
    1.2%
    326
    +0.10
    0.6%
    173
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    727
    +0.21
    0.06
    173
    +0.10
    0.05
    326
    +0.08
    0.14
    Negative Logits
    Catalog
    -0.59
    inen
    -0.58
    ANS
    -0.56
    ---------------
    -0.55
    arov
    -0.53
    Herm
    -0.51
    arthy
    -0.51
    operated
    -0.51
    Grant
    -0.50
    HOU
    -0.50
    POSITIVE LOGITS
     smoking
    0.88
    ters
    0.81
    ting
    0.75
     Smoking
    0.72
     Quit
    0.67
     quitting
    0.64
     eating
    0.57
     whining
    0.56
    smoking
    0.55
     quit
    0.53
    Activations Density 4.139%

    No Known Activations