© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13244
    Prev
    Next
    INDEX
    Explanations

    personal pronouns for family members

    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
    393
    +0.31
    1.1%
    362
    +0.16
    0.6%
    298
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.31
    0.18
    15
    +0.16
    0.15
    92
    +0.16
    0.13
    Negative Logits
    vine
    -1.07
    note
    -0.98
    haus
    -0.93
     Beg
    -0.91
    river
    -0.90
     Faster
    -0.90
    âģ
    -0.90
     Included
    -0.89
    cour
    -0.88
    Chall
    -0.87
    POSITIVE LOGITS
     own
    2.58
    self
    1.84
     surroundings
    1.57
     knees
    1.50
    selves
    1.46
     usual
    1.45
     neighbour
    1.44
     peers
    1.43
     newfound
    1.42
     respective
    1.38
    Activations Density 2.225%

    No Known Activations