© 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. 40512
    Prev
    Next
    INDEX
    Explanations

    outbreaks of violence or conflict, whether it be physical altercations, wars, or prison escapes

    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
    553
    +0.15
    0.7%
    391
    +0.12
    0.5%
    717
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.15
    0.07
    761
    +0.12
    0.07
    271
    +0.12
    0.04
    Negative Logits
    anan
    -0.70
     banished
    -0.69
     miss
    -0.68
     vetoed
    -0.65
    antry
    -0.64
     postp
    -0.64
     retired
    -0.62
     misses
    -0.61
     instituted
    -0.60
     deprecated
    -0.59
    POSITIVE LOGITS
     cloves
    0.70
    ymes
    0.70
    å§
    0.68
    Activity
    0.66
    Sax
    0.66
    quished
    0.66
    Loop
    0.64
    rils
    0.64
     candles
    0.63
     valves
    0.62
    Activations Density 4.129%

    No Known Activations