© 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. 3653
    Prev
    Next
    INDEX
    Explanations

    reply/comment threads in a forum or online platform

    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
    529
    +0.04
    0.6%
    293
    +0.03
    0.5%
    539
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.04
    -0.19
    640
    +0.03
    0.21
    393
    +0.03
    0.22
    Negative Logits
     Galile
    -0.21
     Pound
    -0.20
     saves
    -0.20
     ingest
    -0.20
     rounding
    -0.19
     speed
    -0.19
     baptism
    -0.19
     IV
    -0.19
     vomit
    -0.18
     upside
    -0.18
    POSITIVE LOGITS
    roxy
    0.25
    artment
    0.24
    rox
    0.23
    artments
    0.23
    aram
    0.23
    vice
    0.23
    ieft
    0.22
    udeb
    0.22
    vertisements
    0.21
    hyde
    0.21
    Activations Density 9.202%

    No Known Activations