© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31428
    Prev
    Next
    INDEX
    Explanations

    information related to various locations, events, and historical contexts

    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
    756
    +0.04
    0.5%
    512
    +0.04
    0.5%
    460
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    704
    +0.04
    0.05
    373
    +0.04
    -0.20
    132
    +0.03
    0.08
    Negative Logits
    gow
    -0.28
    ItemTracker
    -0.26
    umin
    -0.24
     obstruct
    -0.22
    buy
    -0.21
    cussion
    -0.21
    matic
    -0.21
     Hib
    -0.21
    recomm
    -0.20
    lua
    -0.20
    POSITIVE LOGITS
    Sept
    0.28
    dated
    0.26
    endment
    0.25
    cember
    0.25
    ANI
    0.24
     arrival
    0.23
    Ħ¢
    0.23
    ilant
    0.22
     onset
    0.22
    INA
    0.22
    Activations Density 10.132%

    No Known Activations