© 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. 168
    Prev
    Next
    INDEX
    Explanations

    words related to flying

    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
    326
    +0.18
    0.6%
    269
    +0.16
    0.5%
    553
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.05
    469
    +0.16
    0.04
    603
    +0.13
    0.04
    Negative Logits
    ortium
    -1.22
    essee
    -1.19
    ãĥ¤
    -1.07
    illian
    -1.05
    orians
    -1.03
     Cumber
    -1.03
    orr
    -1.03
    uary
    -1.01
    ointed
    -0.99
    Developer
    -0.99
    POSITIVE LOGITS
    wheel
    1.48
    walk
    1.36
    hawk
    1.32
    plane
    1.27
    whe
    1.26
    hawks
    1.15
    leaf
    1.13
    walking
    1.12
     Mirage
    1.12
    weight
    1.10
    Activations Density 0.772%

    No Known Activations