© 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. 37106
    Prev
    Next
    INDEX
    Explanations

    instances where certain entities are described as having similar attributes or behaviors

    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
    447
    +0.24
    1.1%
    438
    +0.11
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.24
    0.10
    362
    +0.11
    0.10
    561
    +0.10
    0.09
    Negative Logits
    OST
    -0.74
    arden
    -0.71
    oway
    -0.65
    phasis
    -0.64
     Beans
    -0.63
    ribution
    -0.62
     Lauderdale
    -0.61
    UME
    -0.60
     Shoals
    -0.59
     Gamer
    -0.59
    POSITIVE LOGITS
     vein
    1.02
     sized
    0.98
     fate
    0.89
    worldly
    0.89
    minded
    0.88
     minded
    0.85
     amounts
    0.85
    lihood
    0.84
     twins
    0.81
     sentiments
    0.79
    Activations Density 9.326%

    No Known Activations