© 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. 11481
    Prev
    Next
    INDEX
    Explanations

    phrases related to delays or holding back actions

    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
    288
    +0.19
    0.6%
    286
    +0.18
    0.6%
    271
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.10
    271
    +0.18
    0.05
    286
    +0.17
    0.05
    Negative Logits
    ortium
    -1.23
    tained
    -1.16
    ramid
    -1.13
    bold
    -1.10
    ophe
    -1.06
    \\\\\\\\
    -1.06
    arov
    -1.02
    ergy
    -1.02
    onym
    -1.02
    ocene
    -1.02
    POSITIVE LOGITS
     gratification
    1.47
     indefinitely
    1.26
     delaying
    1.23
     cooker
    1.21
     postp
    1.13
     puberty
    1.08
     delays
    1.07
    poke
    1.04
     til
    1.02
     delayed
    1.02
    Activations Density 1.650%

    No Known Activations