© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5625
    Prev
    Next
    INDEX
    Explanations

    phrases related to issuing apologies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.23
    0.8%
    35
    +0.18
    0.6%
    377
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.07
    151
    +0.18
    0.06
    274
    +0.17
    0.05
    Negative Logits
    weeney
    -1.26
    arnaev
    -1.11
    ulhu
    -1.01
    umbers
    -1.01
    need
    -0.99
    estial
    -0.98
    ccording
    -0.98
    picking
    -0.95
    population
    -0.94
    aida
    -0.94
    POSITIVE LOGITS
    giving
    1.34
     unres
    1.30
     apologized
    1.18
     apologize
    1.16
     apology
    1.11
     apologies
    1.09
     apologised
    1.07
     acknowled
    1.04
     forgiveness
    1.04
     apologizing
    1.03
    Activations Density 0.887%

    No Known Activations