© 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. 6043
    Prev
    Next
    INDEX
    Explanations

    news-related information with a focus on specific events or incidents

    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
    434
    +0.14
    0.5%
    279
    +0.13
    0.4%
    103
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.14
    0.07
    284
    +0.13
    0.08
    103
    +0.13
    0.08
    Negative Logits
    ernels
    -1.22
    glomer
    -1.21
    abase
    -1.18
    orsche
    -1.16
    merce
    -1.11
    onomy
    -1.11
    iqueness
    -1.10
     stake
    -1.07
    ebus
    -1.05
    arton
    -1.04
    POSITIVE LOGITS
    ÙĨ
    1.78
    ا
    1.68
    ر
    1.61
    Ùħ
    1.59
    ÙĦ
    1.59
    ãģ®
    1.55
    Ù
    1.55
    ÙĬ
    1.54
    ãģ®ç
    1.54
    ب
    1.52
    Activations Density 0.420%

    No Known Activations