© 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. 7013
    Prev
    Next
    INDEX
    Explanations

    mentions of quotas in various contexts, such as job selection, resource utilization, and humanitarian aid

    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
    617
    +0.05
    0.4%
    216
    +0.05
    0.4%
    508
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.05
    0.03
    575
    +0.05
    0.02
    222
    +0.04
    0.02
    Negative Logits
    lly
    -0.39
     heartbeat
    -0.36
    itiz
    -0.34
     fingert
    -0.33
    lege
    -0.32
    joy
    -0.32
    ovember
    -0.30
    chair
    -0.30
    strap
    -0.30
     fingertips
    -0.29
    POSITIVE LOGITS
     quotas
    0.49
     quota
    0.46
     tracts
    0.33
     Hels
    0.32
     Pengu
    0.31
    inant
    0.30
    ãĤ»
    0.30
    è¦ļéĨĴ
    0.29
     manga
    0.29
    aca
    0.29
    Activations Density 0.105%

    No Known Activations