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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 12877
    Prev
    Next
    INDEX
    Explanations

    technical terms related to medical imaging and medical procedures

    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
    +0.13
    0.6%
    571
    +0.13
    0.6%
    587
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.18
    555
    +0.13
    0.07
    709
    +0.11
    0.10
    Negative Logits
    mint
    -0.82
    istani
    -0.76
    atoon
    -0.72
    atchewan
    -0.64
    ULAR
    -0.62
    adium
    -0.58
    EED
    -0.58
    ivity
    -0.58
    اÙĦ
    -0.57
    ï
    -0.57
    POSITIVE LOGITS
    ewitness
    1.05
    kj
    0.89
    estinal
    0.77
    er
    0.75
    outube
    0.72
    oshi
    0.71
    esy
    0.70
    alty
    0.69
    wolf
    0.68
    vironment
    0.67
    Activations Density 5.377%

    No Known Activations