© 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. 2388
    Prev
    Next
    INDEX
    Explanations

    the name "Ajay"

    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
    26
    +0.16
    0.5%
    709
    +0.16
    0.5%
    420
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.05
    26
    +0.16
    0.05
    701
    +0.14
    0.04
    Negative Logits
    ipeg
    -1.26
    ãĤ´ãĥ³
    -1.08
    hester
    -1.06
    éĹĺ
    -1.06
    etsk
    -1.01
    İĭ
    -1.00
     Archdemon
    -0.99
    ugal
    -0.98
     mund
    -0.96
    女
    -0.94
    POSITIVE LOGITS
    cott
    1.29
    rand
    1.22
    alam
    1.19
    nor
    1.17
    walk
    1.15
    walking
    1.14
    mare
    1.14
    away
    1.09
    oning
    1.09
    ride
    1.08
    Activations Density 1.013%

    No Known Activations