© 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. 40698
    Prev
    Next
    INDEX
    Explanations

    phrases related to magnets and magnetic fields

    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
    288
    +0.16
    0.7%
    447
    +0.14
    0.6%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.16
    0.02
    326
    +0.14
    0.17
    665
    +0.11
    0.10
    Negative Logits
    ership
    -0.77
    soDeliveryDate
    -0.75
    20439
    -0.75
    ULTS
    -0.73
    semble
    -0.69
     Kut
    -0.69
     Columb
    -0.68
    akings
    -0.67
    IRD
    -0.67
    ctive
    -0.66
    POSITIVE LOGITS
    netic
    1.15
     resonance
    1.08
     Reson
    0.91
     coils
    0.83
     monop
    0.83
     stripe
    0.83
     compass
    0.83
     magnetic
    0.82
     susceptibility
    0.82
     magnets
    0.81
    Activations Density 5.862%

    No Known Activations