© 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. 2214
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and software development

    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
    71
    +0.05
    0.5%
    117
    +0.04
    0.4%
    369
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    547
    +0.05
    0.01
    476
    +0.04
    0.01
    687
    +0.04
    0.01
    Negative Logits
    redible
    -0.29
    mouth
    -0.29
    hare
    -0.28
    ween
    -0.28
    udic
    -0.28
    clusive
    -0.27
    utan
    -0.27
    atin
    -0.27
    uries
    -0.26
    yn
    -0.26
    POSITIVE LOGITS
     incorpor
    0.32
     guiActiveUnfocused
    0.32
    semble
    0.31
     Parables
    0.31
     Practices
    0.29
    quartered
    0.27
     Farms
    0.26
     reap
    0.26
     authent
    0.26
     IMAGES
    0.26
    Activations Density 0.057%

    No Known Activations