© 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. 34054
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an expected outcome or intention

    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
    613
    +0.13
    0.5%
    431
    +0.11
    0.4%
    762
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.13
    0.19
    566
    +0.11
    0.11
    55
    +0.11
    0.13
    Negative Logits
     Fine
    -0.74
    ILE
    -0.74
     Katy
    -0.74
     complicate
    -0.71
     Panic
    -0.71
     Indust
    -0.70
     Surprise
    -0.69
     Dism
    -0.69
     Stern
    -0.68
     Amateur
    -0.68
    POSITIVE LOGITS
     wont
    0.84
    Ont
    0.83
    alian
    0.81
    elf
    0.81
    burgh
    0.79
    ptr
    0.77
     existed
    0.75
     iP
    0.75
     regener
    0.73
    liner
    0.73
    Activations Density 6.067%

    No Known Activations