© 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. 4815
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Island"

    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
    +0.29
    1.2%
    195
    +0.15
    0.6%
    566
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.29
    0.29
    138
    +0.15
    0.26
    64
    +0.11
    -0.22
    Negative Logits
    ãģĮ
    -0.89
    theless
    -0.79
     cleaners
    -0.72
    ruciating
    -0.69
    è£
    -0.69
     takedown
    -0.69
    è¦ļéĨĴ
    -0.68
    åij
    -0.67
     stitches
    -0.67
     restraints
    -0.67
    POSITIVE LOGITS
    olated
    1.54
    olation
    1.41
    olate
    1.34
    peria
    1.33
    abella
    1.32
    htar
    1.21
    ilon
    1.20
    rael
    1.15
    sei
    1.10
    ync
    1.09
    Activations Density 11.643%

    No Known Activations