© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32816
    Prev
    Next
    INDEX
    Explanations

    Slavic names, particularly those with the suffix "-is" or "-us"

    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
    195
    +0.19
    0.7%
    447
    +0.19
    0.7%
    578
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.19
    0.17
    208
    +0.19
    0.13
    620
    +0.14
    0.03
    Negative Logits
    ¥ŀ
    -1.03
    ruciating
    -0.91
    è¦ļéĨĴ
    -0.82
    ¥µ
    -0.80
    ishers
    -0.79
     reconc
    -0.75
     manners
    -0.74
    ished
    -0.74
     thumbnail
    -0.73
    osponsors
    -0.71
    POSITIVE LOGITS
    abeth
    1.50
    peed
    1.31
    earch
    1.21
    aurus
    1.20
    olate
    1.10
    olation
    1.09
    ippi
    1.08
    rael
    1.06
    pora
    1.06
    sel
    1.04
    Activations Density 10.940%

    No Known Activations