© 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. 35026
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and systems architecture

    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
    +0.25
    1.1%
    232
    +0.12
    0.5%
    479
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.25
    0.17
    6
    +0.12
    0.17
    556
    +0.11
    0.13
    Negative Logits
     carbohyd
    -0.99
    etheless
    -0.91
    yss
    -0.86
     tremend
    -0.84
     satell
    -0.83
    amous
    -0.82
    sembly
    -0.76
    alysed
    -0.76
    arently
    -0.75
    yond
    -0.75
    POSITIVE LOGITS
     Association
    1.26
     Suite
    1.10
     Orchestra
    1.03
     Service
    1.01
     Ltd
    1.01
     Disorder
    1.01
     Forum
    1.00
     Index
    1.00
     Club
    0.99
     Clinic
    0.99
    Activations Density 11.462%

    No Known Activations