© 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. 12867
    Prev
    Next
    INDEX
    Explanations

    nouns related to social media content, such as images, captions, messages, and posts on platforms like Facebook

    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
    447
    +0.22
    1.1%
    547
    +0.10
    0.5%
    679
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.22
    0.10
    247
    +0.10
    0.08
    644
    +0.09
    0.10
    Negative Logits
    ãĥĥãĥī
    -0.69
    ãģĦ
    -0.69
    äºĶ
    -0.67
    NetMessage
    -0.64
    ãĤ¤ãĥĪ
    -0.61
    ãĤª
    -0.61
    elsius
    -0.60
    çķ
    -0.59
    èª
    -0.59
     procedural
    -0.58
    POSITIVE LOGITS
     Anon
    0.81
    lain
    0.74
    ebin
    0.73
     VK
    0.65
     devoted
    0.64
     www
    0.63
     username
    0.63
    âĢİ
    0.62
    ifier
    0.62
     "@
    0.61
    Activations Density 8.192%

    No Known Activations