© 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. 33926
    Prev
    Next
    INDEX
    Explanations

    mathematical summations or sums within texts

    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
    +0.16
    0.6%
    314
    +0.14
    0.6%
    167
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.16
    0.43
    138
    +0.14
    0.42
    64
    +0.11
    -0.15
    Negative Logits
     livest
    -0.80
     surn
    -0.79
     Kers
    -0.73
     Defenders
    -0.73
     Ferry
    -0.73
     blinking
    -0.69
     Flame
    -0.69
     foreclosure
    -0.68
    ussen
    -0.65
     ignition
    -0.65
    POSITIVE LOGITS
    ming
    1.70
    mits
    1.32
    mers
    1.31
    otaur
    1.11
    sum
    1.04
    ulative
    1.04
    atra
    1.01
     sum
    0.99
    mes
    0.96
    iture
    0.96
    Activations Density 6.445%

    No Known Activations