© 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. 8500
    Prev
    Next
    INDEX
    Explanations

    words related to technology, particularly mentions of zones or particular terms like "zephyr."

    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
    384
    +0.13
    0.5%
    116
    +0.13
    0.5%
    649
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.12
    659
    +0.13
    0.10
    288
    +0.12
    0.12
    Negative Logits
    luent
    -1.03
    anooga
    -0.95
    ndra
    -0.94
    uctor
    -0.92
     glim
    -0.91
    croft
    -0.85
    matter
    -0.84
    erest
    -0.83
    raising
    -0.83
    ntil
    -0.82
    POSITIVE LOGITS
    ombie
    1.16
    ombies
    1.11
    ebra
    1.04
    odiac
    0.87
    hao
    0.86
    ealous
    0.85
    arro
    0.82
    oning
    0.81
    oom
    0.81
     Oo
    0.80
    Activations Density 2.279%

    No Known Activations