© 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. 11503
    Prev
    Next
    INDEX
    Explanations

    repetitive patterns of code

    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
    195
    +0.20
    0.7%
    566
    +0.14
    0.5%
    487
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.20
    0.19
    102
    +0.14
    0.17
    566
    +0.13
    0.14
    Negative Logits
     takedown
    -1.00
    ruciating
    -0.97
    ãģĮ
    -0.91
     chants
    -0.83
    ãģ®å®
    -0.82
    è£
    -0.82
     ABE
    -0.80
     cleaners
    -0.80
    è¦ļéĨĴ
    -0.80
    OSE
    -0.79
    POSITIVE LOGITS
    olation
    1.60
    olate
    1.59
    rael
    1.49
    olated
    1.42
    peria
    1.41
    abella
    1.36
    kell
    1.28
    htar
    1.24
    n
    1.22
    abel
    1.22
    Activations Density 3.162%

    No Known Activations