Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34187
    Prev
    Next
    INDEX
    Explanations

    words related to medicine, drug development, medical imaging, pharmacology, laboratory experiments, and healthcare advancements

    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
    +0.23
    0.9%
    508
    +0.12
    0.5%
    516
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.23
    0.07
    524
    +0.12
    0.08
    328
    +0.11
    0.04
    Negative Logits
    iland
    -0.86
    adia
    -0.81
     Emir
    -0.80
    auga
    -0.80
    ornia
    -0.79
     Doctrine
    -0.78
    orian
    -0.76
    orthern
    -0.76
     Eag
    -0.75
    cession
    -0.75
    POSITIVE LOGITS
     medications
    1.20
     medication
    1.14
     therape
    1.12
     treatments
    1.09
     drugs
    1.09
     therapies
    1.09
     injections
    1.06
     dosage
    1.06
     overdose
    1.05
     regimen
    1.05
    Activations Density 7.373%

    No Known Activations