© 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. 12926
    Prev
    Next
    INDEX
    Explanations

    figurative language and expressions

    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
    203
    +0.13
    0.7%
    383
    +0.11
    0.6%
    32
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.15
    23
    +0.11
    0.13
    575
    +0.09
    0.17
    Negative Logits
    arching
    -0.72
     Unified
    -0.68
    guard
    -0.68
     guiActiveUnfocused
    -0.64
    Redd
    -0.61
    EFF
    -0.60
    mail
    -0.57
    PLIED
    -0.57
    selection
    -0.56
    wash
    -0.55
    POSITIVE LOGITS
    atively
    0.99
    ative
    0.95
     figur
    0.89
    orical
    0.85
    tery
    0.81
    ties
    0.74
    arge
    0.68
     Meaning
    0.68
    oric
    0.66
    atform
    0.66
    Activations Density 7.565%

    No Known Activations