© 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. 33782
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or organizations, particularly related to news or events happening in those locations

    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
    +0.21
    0.8%
    496
    +0.16
    0.6%
    288
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.21
    0.07
    116
    +0.16
    0.07
    667
    +0.15
    0.06
    Negative Logits
     Qiao
    -0.93
    ãĥł
    -0.91
    oward
    -0.91
    \\\\\\\\
    -0.90
     ACTIONS
    -0.89
    ouse
    -0.88
    uracy
    -0.88
    uously
    -0.88
    IGHTS
    -0.87
    isted
    -0.87
    POSITIVE LOGITS
    plex
    1.31
     Manila
    1.16
    jet
    1.10
    PC
    1.00
     Transit
    0.94
    active
    0.93
    Plex
    0.90
    biology
    0.88
    roads
    0.88
    pton
    0.87
    Activations Density 4.980%

    No Known Activations