© 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. 33835
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions like hatred and distrust

    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
    +0.18
    1.0%
    199
    +0.09
    0.5%
    161
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.18
    0.09
    720
    +0.09
    0.09
    199
    +0.09
    0.13
    Negative Logits
    aqu
    -0.64
    inventoryQuantity
    -0.59
    annis
    -0.55
    pletion
    -0.55
    umm
    -0.55
    orage
    -0.54
     helicop
    -0.54
     Horizon
    -0.54
    atonin
    -0.54
    changes
    -0.52
    POSITIVE LOGITS
     hated
    0.66
    lessly
    0.65
     hatred
    0.62
     toward
    0.61
     prejudice
    0.61
     vengeance
    0.61
    ãĥĨ
    0.61
     towards
    0.60
    ¿½
    0.58
    fully
    0.58
    Activations Density 8.367%

    No Known Activations