© 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. 46000
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of awe, amazement, or admiration within a variety of contexts

    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
    119
    +0.11
    0.6%
    377
    +0.11
    0.6%
    383
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.22
    283
    +0.11
    -0.01
    129
    +0.09
    0.05
    Negative Logits
     Luxem
    -0.65
    cision
    -0.63
     Gemini
    -0.63
    姫
    -0.62
    士
    -0.62
    phrine
    -0.62
    xual
    -0.59
     Kaepernick
    -0.57
     iod
    -0.56
     Feld
    -0.56
    POSITIVE LOGITS
    akens
    1.04
    akening
    0.90
    kward
    0.88
    erness
    0.79
    iring
    0.74
    arak
    0.73
    ards
    0.72
    aw
    0.72
    atche
    0.72
    orld
    0.72
    Activations Density 10.883%

    No Known Activations