© 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. 34041
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and accusations

    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
    +0.24
    1.0%
    640
    +0.15
    0.7%
    124
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.24
    0.27
    393
    +0.15
    0.22
    745
    +0.13
    -0.11
    Negative Logits
     Phi
    -0.84
    ulhu
    -0.81
     Compass
    -0.77
    Ń·
    -0.73
     Slide
    -0.73
     Confederation
    -0.72
     TAMADRA
    -0.72
     Noir
    -0.72
     Pok
    -0.71
     Bravo
    -0.70
    POSITIVE LOGITS
    enough
    1.28
    sized
    1.23
    connected
    1.21
    defined
    1.17
    equipped
    1.17
    trained
    1.16
    known
    1.15
    appointed
    1.13
    established
    1.13
    placed
    1.12
    Activations Density 9.510%

    No Known Activations