© 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. 14072
    Prev
    Next
    INDEX
    Explanations

    phrases related to roles and responsibilities in various contexts

    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
    •Layer 6 UMAP region: Mixed in middle - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.23
    1.0%
    321
    +0.14
    0.6%
    679
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.23
    0.28
    362
    +0.14
    0.15
    385
    +0.14
    0.17
    Negative Logits
    False
    -0.79
     Bulg
    -0.75
    Latest
    -0.70
    bones
    -0.68
    ãĥ©ãĥ³
    -0.68
     Uri
    -0.67
    undred
    -0.66
    REAM
    -0.66
     Rapt
    -0.66
    Rail
    -0.65
    POSITIVE LOGITS
    playing
    1.09
     roles
    1.04
     reversal
    0.95
     role
    0.88
    model
    0.85
    role
    0.79
    entials
    0.78
    acter
    0.77
     models
    0.77
     model
    0.76
    Activations Density 13.142%

    No Known Activations