© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2639
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "ung", which could potentially be a specific term or topic mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    679
    +0.18
    0.6%
    649
    +0.17
    0.6%
    276
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.05
    659
    +0.17
    0.04
    232
    +0.14
    0.03
    Negative Logits
    âĸijâĸij
    -1.02
    ãĥ¯ãĥ³
    -1.01
    IDER
    -1.01
    cloth
    -0.99
    urity
    -0.99
    Brexit
    -0.95
    afort
    -0.93
    Effective
    -0.92
    aving
    -0.87
    VID
    -0.87
    POSITIVE LOGITS
    lasses
    1.78
    nir
    1.34
    regate
    1.28
    sung
    1.21
    undo
    1.20
    sam
    1.15
    oing
    1.15
    lass
    1.15
    swick
    1.15
    emouth
    1.12
    Activations Density 0.624%

    No Known Activations