© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36508
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms related to genetic modifications or chemicals

    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
    480
    +0.24
    1.3%
    447
    +0.20
    1.1%
    464
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.24
    -0.22
    266
    +0.20
    0.80
    351
    +0.12
    0.06
    Negative Logits
     Lia
    -0.60
    qq
    -0.50
    spe
    -0.50
    nah
    -0.49
    ARA
    -0.49
    arr
    -0.49
     Pesh
    -0.47
    ð
    -0.47
    arp
    -0.47
     Seah
    -0.46
    POSITIVE LOGITS
     compound
    0.60
    tesy
    0.53
    Guest
    0.50
     Dudley
    0.48
    monary
    0.47
    ioxide
    0.47
     drag
    0.47
     Freddie
    0.46
     Drag
    0.46
     jog
    0.46
    Activations Density 75.696%

    No Known Activations