Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 40226
    Prev
    Next
    INDEX
    Explanations

    words related to bitterness and conflict

    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
    0.8%
    632
    +0.09
    0.5%
    666
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.16
    0.11
    444
    +0.09
    0.07
    666
    +0.09
    0.07
    Negative Logits
    nesota
    -0.81
    arlane
    -0.73
    upload
    -0.73
    ulhu
    -0.71
    iques
    -0.70
    aver
    -0.70
    utations
    -0.69
    allows
    -0.67
    aucus
    -0.67
    ansion
    -0.67
    POSITIVE LOGITS
     bitter
    0.91
    terness
    0.83
     parting
    0.83
     bitterness
    0.80
     irony
    0.77
     disappointment
    0.76
     cold
    0.74
     spo
    0.72
     bitterly
    0.71
     streaks
    0.70
    Activations Density 8.730%

    No Known Activations