© 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 Local
    9. 6-RES_SCL-AJT
    11. 39586
    Prev
    Next
    INDEX
    Explanations

    mentions of buckwheat

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    526
    +0.13
    0.7%
    326
    +0.12
    0.6%
    316
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.13
    0.09
    141
    +0.12
    0.07
    314
    +0.12
    -0.04
    Negative Logits
    anyahu
    -0.62
     Scope
    -0.58
     Sloan
    -0.58
     SERVICE
    -0.57
    ãĥīãĥ©ãĤ´ãĥ³
    -0.57
    apist
    -0.57
    istically
    -0.56
     è£ıè¦ļéĨĴ
    -0.56
    20439
    -0.56
    udic
    -0.55
    POSITIVE LOGITS
    whe
    1.01
    minster
    0.98
    ling
    0.85
    ner
    0.82
    aroo
    0.81
    keye
    0.80
    led
    0.80
     buck
    0.79
    heit
    0.77
    buck
    0.77
    Activations Density 6.163%

    No Known Activations