© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34749
    Prev
    Next
    INDEX
    Explanations

    words related to understanding, comprehension, and lack of understanding in a context concerning various topics such as opinions, games, communication, climate change, and personal stories

    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
    +0.20
    1.1%
    154
    +0.11
    0.6%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.31
    255
    +0.11
    0.11
    640
    +0.10
    0.25
    Negative Logits
    erity
    -0.77
    uable
    -0.66
    elight
    -0.64
    iaries
    -0.63
    uxe
    -0.60
    etheus
    -0.60
    icides
    -0.59
     roundup
    -0.59
    ijah
    -0.58
    raviolet
    -0.57
    POSITIVE LOGITS
     workings
    0.77
     nuances
    0.66
     WHY
    0.66
     dynamics
    0.64
     Situation
    0.63
     intric
    0.63
     concepts
    0.63
     psychology
    0.61
    LAB
    0.60
     gist
    0.60
    Activations Density 13.737%

    No Known Activations