© 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
    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. 13095
    Prev
    Next
    INDEX
    Explanations

    instances of words indicating collaboration or being together with someone or something

    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
    +0.21
    1.3%
    679
    +0.10
    0.6%
    549
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.23
    608
    +0.10
    0.25
    572
    +0.08
    0.14
    Negative Logits
    chin
    -0.61
    jab
    -0.54
    ek
    -0.54
    asse
    -0.54
    aced
    -0.52
    itar
    -0.52
    ck
    -0.52
    endiary
    -0.51
    nery
    -0.51
    auld
    -0.50
    POSITIVE LOGITS
    lihood
    0.58
    ++++
    0.51
     hers
    0.50
    GROUND
    0.49
     Shiva
    0.49
    ÃįÃį
    0.49
    side
    0.48
     peers
    0.47
     fellow
    0.47
    pins
    0.47
    Activations Density 10.791%

    No Known Activations