© 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. 46035
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases containing the word "By" preceeding a number

    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
    •Layer 6 UMAP region: Mostly-local cluster on left - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.29
    1.1%
    616
    +0.14
    0.5%
    393
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.29
    0.07
    559
    +0.14
    0.08
    393
    +0.12
    0.21
    Negative Logits
    SPONSORED
    -0.94
    atem
    -0.93
    hyde
    -0.82
    isable
    -0.80
    abs
    -0.76
    blast
    -0.73
    >)
    -0.73
    ptive
    -0.72
    inea
    -0.72
    اÙĦ
    -0.71
    POSITIVE LOGITS
     contrast
    1.34
     virtue
    1.24
    akuya
    1.16
     implication
    1.02
    catch
    1.00
    stand
    0.89
     extension
    0.89
     default
    0.89
     sheer
    0.88
     definition
    0.87
    Activations Density 9.211%

    No Known Activations