© 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 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. 12949
    Prev
    Next
    INDEX
    Explanations

    details related to weather patterns and geographic locations

    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
    679
    +0.21
    0.8%
    393
    +0.19
    0.7%
    549
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.21
    0.07
    572
    +0.19
    0.06
    203
    +0.14
    0.06
    Negative Logits
    lees
    -1.04
    isible
    -0.95
    gamer
    -0.95
    ared
    -0.92
    tnc
    -0.91
    eyed
    -0.91
    bound
    -0.89
    eds
    -0.89
    Bas
    -0.89
    aq
    -0.88
    POSITIVE LOGITS
     fortunately
    1.19
     admittedly
    1.12
     preferably
    1.09
    soever
    1.07
     interestingly
    1.07
     thankfully
    1.05
     they
    1.02
     sadly
    1.01
     luckily
    1.01
    tons
    0.97
    Activations Density 0.938%

    No Known Activations