© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 37174
    Prev
    Next
    INDEX
    Explanations

    seemingly random characters and symbols, possibly due to encoding issues

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    201
    +0.14
    0.6%
    216
    +0.14
    0.6%
    728
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.14
    0.09
    99
    +0.14
    0.08
    728
    +0.14
    0.05
    Negative Logits
    ideon
    -0.98
    abase
    -0.97
    aminer
    -0.90
    mented
    -0.90
    ividual
    -0.89
    irtual
    -0.88
    iov
    -0.87
    lyak
    -0.85
    alus
    -0.84
    ierrez
    -0.82
    POSITIVE LOGITS
    ا
    1.38
    Ù
    1.36
    اØ
    1.33
    Ùĩ
    1.29
    ÙĬ
    1.20
    Í
    1.13
    Ùħ
    1.13
    ÙĪ
    1.12
    ت
    1.06
    Ùİ
    1.06
    Activations Density 3.734%

    No Known Activations