© 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. 12727
    Prev
    Next
    INDEX
    Explanations

    German words, possibly related to politics and philosophy, with a focus on certain characters like ö, ü, and ß

    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
    +0.19
    0.7%
    377
    +0.13
    0.5%
    326
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    666
    +0.19
    0.09
    748
    +0.13
    0.04
    97
    +0.13
    0.05
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.85
    channelAvailability
    -0.83
    NESS
    -0.82
    terday
    -0.81
    ãĤ¶
    -0.80
     FANT
    -0.78
     Classics
    -0.77
    bilt
    -0.77
     PID
    -0.77
    Ùħ
    -0.77
    POSITIVE LOGITS
    atmeal
    1.45
    phthal
    1.34
    mbudsman
    1.32
    mbuds
    1.28
    ops
    1.27
    lymp
    1.26
    vernight
    1.23
    tto
    1.22
    lder
    1.22
    vals
    1.22
    Activations Density 6.856%

    No Known Activations