© 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. 35053
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to materials, cellular structures, and bodily functions

    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
    669
    +0.13
    0.6%
    575
    +0.13
    0.6%
    40
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.13
    0.11
    656
    +0.13
    0.08
    738
    +0.11
    0.06
    Negative Logits
     Victory
    -0.89
     Valhalla
    -0.88
    xual
    -0.82
    wick
    -0.78
    reon
    -0.75
    åĭ
    -0.75
     Osiris
    -0.75
    ership
    -0.72
    anooga
    -0.72
    swick
    -0.72
    POSITIVE LOGITS
    organisms
    1.26
     organisms
    1.12
    phthal
    1.08
    seconds
    1.03
     spores
    1.02
     microscopic
    1.01
     sized
    1.00
     particles
    0.95
    cules
    0.94
     pores
    0.93
    Activations Density 8.932%

    No Known Activations