© 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. 8169
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    152
    +0.27
    0.9%
    167
    +0.14
    0.4%
    352
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.27
    0.08
    531
    +0.14
    0.05
    352
    +0.13
    0.05
    Negative Logits
    aneously
    -1.19
    aneous
    -1.09
    iferation
    -1.03
    iation
    -0.98
    istical
    -0.93
    DragonMagazine
    -0.92
    yz
    -0.92
    vernment
    -0.92
    iant
    -0.91
     Mayer
    -0.90
    POSITIVE LOGITS
    wife
    2.08
    wives
    1.97
    keeping
    1.66
    mates
    1.60
    boats
    1.53
    boat
    1.50
    keeper
    1.46
    warming
    1.44
    mate
    1.43
    plant
    1.38
    Activations Density 0.897%

    No Known Activations