© 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. 32733
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology, software, and information

    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
    509
    +0.08
    0.4%
    273
    +0.07
    0.4%
    240
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.08
    0.12
    195
    +0.07
    0.03
    240
    +0.07
    0.09
    Negative Logits
    kamp
    -0.61
    arantine
    -0.55
    çķ
    -0.53
    emale
    -0.53
     Banner
    -0.52
    ourses
    -0.51
    è¦ļéĨĴ
    -0.49
    rift
    -0.48
    iership
    -0.47
    ropolis
    -0.47
    POSITIVE LOGITS
    ifully
    0.75
    surprisingly
    0.71
    wise
    0.68
    ONSORED
    0.67
    rary
    0.67
     unsurprisingly
    0.64
    prisingly
    0.64
    hematically
    0.64
    ily
    0.63
    identally
    0.63
    Activations Density 4.263%

    No Known Activations