© 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. 5024
    Prev
    Next
    INDEX
    Explanations

    phrases related to saving or preserving something, whether it be people, animals, traditions, or items

    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
    71
    +0.10
    0.7%
    270
    +0.07
    0.5%
    321
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.10
    0.10
    176
    +0.07
    0.06
    708
    +0.07
    0.07
    Negative Logits
    naire
    -0.51
    ysis
    -0.50
     puzz
    -0.50
    mith
    -0.48
    ounced
    -0.47
    issance
    -0.47
    ipal
    -0.45
    auer
    -0.44
    acle
    -0.44
    ial
    -0.41
    POSITIVE LOGITS
    Save
    0.55
    ters
    0.48
    vant
    0.47
    topic
    0.47
    ricular
    0.45
     Yourself
    0.45
     Save
    0.44
     Print
    0.44
     Din
    0.42
     Value
    0.41
    Activations Density 8.917%

    No Known Activations