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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34699
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    64
    +0.23
    2.1%
    447
    +0.22
    2.1%
    87
    +0.20
    1.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.23
    -0.01
    464
    +0.22
    0.23
    459
    +0.20
    0.26
    Negative Logits
     pse
    -0.43
     disadvant
    -0.42
     skelet
    -0.41
     exting
    -0.39
     welf
    -0.38
    ntil
    -0.38
     conflic
    -0.36
     murd
    -0.35
    âĹ¼
    -0.35
     caut
    -0.35
    POSITIVE LOGITS
     [âĢ¦]
    0.46
     âĢİ
    0.45
     ....
    0.41
     âĢº
    0.40
    âĢİ
    0.40
     ...
    0.39
     Posted
    0.39
    20439
    0.37
     Vinyl
    0.35
     Tuesday
    0.33
    Activations Density 18.138%

    No Known Activations