© 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. 33060
    Prev
    Next
    INDEX
    Explanations

    keywords related to Java programming and software development

    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
    447
    +0.22
    1.0%
    288
    +0.16
    0.8%
    316
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.22
    0.07
    641
    +0.16
    0.09
    288
    +0.12
    0.15
    Negative Logits
    ablishment
    -0.77
    chell
    -0.76
     sclerosis
    -0.74
    uers
    -0.73
    mble
    -0.73
    pload
    -0.73
    henko
    -0.72
     proble
    -0.72
    rons
    -0.71
    rification
    -0.70
    POSITIVE LOGITS
     EE
    0.93
    Script
    0.89
    FX
    0.81
    Doc
    0.80
    osph
    0.77
    jar
    0.73
     Beans
    0.71
     Java
    0.71
     Virtual
    0.70
     Pes
    0.68
    Activations Density 5.707%

    No Known Activations