© 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. 13978
    Prev
    Next
    INDEX
    Explanations

    moral or ethical concepts and considerations

    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
    0.8%
    288
    +0.14
    0.6%
    151
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.15
    669
    +0.14
    0.10
    608
    +0.12
    0.16
    Negative Logits
    xual
    -1.03
    lers
    -0.88
    rams
    -0.84
     Pavilion
    -0.82
    hips
    -0.81
    -+
    -0.79
    abee
    -0.79
    essions
    -0.78
    WER
    -0.78
     Herz
    -0.77
    POSITIVE LOGITS
     hazard
    1.20
    istic
    1.19
     compass
    1.14
     equival
    1.06
     conscience
    1.04
    ising
    1.02
    izing
    1.00
    ised
    1.00
    istically
    1.00
     indignation
    0.99
    Activations Density 11.113%

    No Known Activations