© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3627
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial orientation and observation

    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
    386
    +0.14
    0.5%
    246
    +0.13
    0.5%
    642
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.14
    0.04
    333
    +0.13
    0.03
    246
    +0.12
    0.04
    Negative Logits
    TOP
    -0.84
    isma
    -0.83
    EStreamFrame
    -0.81
     Chronic
    -0.80
    glomer
    -0.78
    ĺħ
    -0.77
     Alz
    -0.76
    eros
    -0.75
    RIC
    -0.74
    cia
    -0.74
    POSITIVE LOGITS
    bley
    0.96
    zag
    0.95
    paren
    0.91
     heavens
    0.90
    âĸĪâĸĪâĸĪâĸĪ
    0.89
     positives
    0.89
     afar
    0.87
    lights
    0.87
    ubes
    0.87
    rha
    0.85
    Activations Density 0.693%

    No Known Activations