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. 45291
    Prev
    Next
    INDEX
    Explanations

    information related to nutrition and health benefits of various foods and ingredients

    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
    +0.24
    1.4%
    738
    +0.10
    0.6%
    289
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.24
    0.22
    640
    +0.10
    0.36
    375
    +0.09
    0.09
    Negative Logits
    ipeg
    -0.58
    Own
    -0.54
    idays
    -0.53
    iversary
    -0.52
    ese
    -0.52
    icip
    -0.51
    egal
    -0.51
     Presidents
    -0.50
    swick
    -0.50
    istar
    -0.49
    POSITIVE LOGITS
     crystals
    0.66
    ioxide
    0.66
     chloride
    0.61
     ammon
    0.59
     Gamma
    0.58
     capacitor
    0.57
     synth
    0.57
     ppm
    0.56
     potassium
    0.56
     veins
    0.56
    Activations Density 24.515%

    No Known Activations