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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45148
    Prev
    Next
    INDEX
    Explanations

    information about public protests and demonstrations

    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
    +0.24
    1.2%
    481
    +0.12
    0.6%
    113
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.24
    -0.15
    481
    +0.12
    0.26
    627
    +0.09
    0.06
    Negative Logits
     inherited
    -0.86
     patents
    -0.84
     Inher
    -0.82
     matured
    -0.81
     immortality
    -0.81
     inheritance
    -0.79
     patent
    -0.77
     successor
    -0.76
     inher
    -0.73
     causation
    -0.71
    POSITIVE LOGITS
     chanting
    1.20
     protesters
    1.09
     chants
    1.08
     cheering
    1.05
     demonstrators
    1.04
     chanted
    1.03
     protestors
    1.03
     protest
    0.95
     onlook
    0.94
     cheers
    0.94
    Activations Density 15.294%

    No Known Activations