© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39679
    Prev
    Next
    INDEX
    Explanations

    phrases related to morning routines and preparations for outdoor activities

    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
    1.0%
    481
    +0.17
    0.8%
    221
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.23
    526
    +0.17
    -0.07
    636
    +0.10
    0.15
    Negative Logits
    ère
    -0.71
     hemor
    -0.69
     apologizing
    -0.65
     referring
    -0.63
     thanking
    -0.61
     Luxem
    -0.61
     grouping
    -0.60
     guaranteeing
    -0.60
     telling
    -0.60
    orsi
    -0.60
    POSITIVE LOGITS
    iped
    0.81
    aughs
    0.72
    unks
    0.72
    redients
    0.70
    fits
    0.68
    irds
    0.68
    endas
    0.67
    blers
    0.67
    olitical
    0.66
    cakes
    0.65
    Activations Density 21.150%

    No Known Activations