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

    Neuronpedia

    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. 3181
    Prev
    Next
    INDEX
    Explanations

    phrases related to getting away with something

    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
    568
    +0.05
    0.5%
    501
    +0.05
    0.4%
    588
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.05
    0.02
    568
    +0.05
    0.02
    764
    +0.05
    0.02
    Negative Logits
    ural
    -0.36
    ials
    -0.34
     Uz
    -0.33
    azel
    -0.33
     Yamato
    -0.32
    ulum
    -0.32
    snap
    -0.31
    Emer
    -0.31
    hops
    -0.31
    hari
    -0.30
    POSITIVE LOGITS
     safely
    0.41
     Vend
    0.32
     Horses
    0.31
     Solitaire
    0.30
     Ride
    0.30
    ARM
    0.30
     Riding
    0.30
     horses
    0.29
    ©¶æ
    0.29
     Veh
    0.29
    Activations Density 0.050%

    No Known Activations