© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7589
    Prev
    Next
    INDEX
    Explanations

    locations or travel-related words

    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
    758
    +0.09
    0.6%
    100
    +0.07
    0.5%
    231
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.09
    -0.00
    539
    +0.07
    0.01
    226
    +0.07
    0.01
    Negative Logits
    ortunately
    -0.53
     Sheep
    -0.49
     Intent
    -0.48
    ructure
    -0.48
    anting
    -0.48
    encing
    -0.46
     Mob
    -0.45
    ikuman
    -0.45
     eleph
    -0.44
    xtap
    -0.44
    POSITIVE LOGITS
    QUIRE
    0.51
    window
    0.50
    ][/
    0.49
    true
    0.49
    liness
    0.47
     enthus
    0.46
    ?]
    0.46
    ija
    0.45
     latex
    0.44
    bie
    0.43
    Activations Density 0.008%

    No Known Activations