© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4772
    Prev
    Next
    INDEX
    Explanations

    references to academic and philosophical concepts, such as epistemology, realism, and empiricism

    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
    0.9%
    317
    +0.13
    0.5%
    516
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.22
    0.12
    507
    +0.13
    0.14
    103
    +0.12
    0.11
    Negative Logits
     Leban
    -0.87
    Interstitial
    -0.78
    BALL
    -0.77
    folder
    -0.77
    Alert
    -0.75
    Boss
    -0.74
     VIP
    -0.73
     lia
    -0.72
     registry
    -0.72
     liaison
    -0.72
    POSITIVE LOGITS
    icist
    1.43
     epist
    1.32
     presupp
    1.21
     philosophers
    1.20
     theology
    1.15
     philosoph
    1.14
     Theory
    1.13
    icism
    1.11
    ophical
    1.09
    alogy
    1.09
    Activations Density 13.388%

    No Known Activations