© 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. 4021
    Prev
    Next
    INDEX
    Explanations

    guidelines and restrictions related to personal health and safety

    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
    267
    +0.14
    0.5%
    515
    +0.12
    0.5%
    746
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.17
    232
    +0.12
    0.08
    288
    +0.12
    0.16
    Negative Logits
    Ö¼
    -1.00
     accur
    -0.88
     tomat
    -0.85
     improv
    -0.81
    ãĤ¼
    -0.81
    ortment
    -0.80
    adish
    -0.78
     Madden
    -0.77
     convol
    -0.74
     sophistic
    -0.73
    POSITIVE LOGITS
    geon
    1.68
    geons
    1.56
    nel
    1.54
    nels
    1.35
    ned
    1.35
    ners
    1.34
    idad
    1.33
    cles
    1.28
    culus
    1.25
    fortunately
    1.22
    Activations Density 5.918%

    No Known Activations